Upload folder using huggingface_hub

.gitattributes

@@ -415,3 +415,12 @@ Meta-Llama-3-8B-Instruct_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-1029-sd-42/checkpoint-731/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-1029-sd-42/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-1029-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4866/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-5677/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-6488/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-811/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29626cfdf5fb74581691c2f8a4959a8bfacf991c59dce48b2a56c151db65b924
+size 143153376

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29626cfdf5fb74581691c2f8a4959a8bfacf991c59dce48b2a56c151db65b924
+size 143153376

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fa544b6efd9931c1508e7dd19e79d63a011f1892a4a75470d8ad0d6f14126a
+size 72886650

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd56b345acd204cffc51ffbb4bb8808fb29c4b818fc35e6e1b2c7fc45e0218a0
+size 14244

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b30b8f3b26b2ef091d45bfcbfd165d1a71788a954adc2f9846020c65a033a2
+size 1064

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/special_tokens_map.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer.model

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/trainer_state.json

@@ -0,0 +1,1183 @@
+{
+  "best_metric": 1.238026738166809,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1622,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.331199540887552e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+size 5560

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98412178b503491fd12c8c313e08b1435a95e5943c2c6b15cbb06e57d9f25072
+size 143153376

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c7487133ca2b3ee4617865295c95819332404e64aaf4584cd360c373857d38
+size 72886650

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf62e9954e54ce4054ffe246197c1e5cf5ca07594c06a3d167d20fca185f2ac1
+size 14244

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd9f5f69932f2af95a428f4d1e97bce98fdafea6df5245c7b87d7819fd124b6
+size 1064

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/special_tokens_map.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer.model

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/trainer_state.json

@@ -0,0 +1,1758 @@
+{
+  "best_metric": 1.238026738166809,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 2433,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2496799311331328e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-2433/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+size 5560

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc38cb62d14fbd06e9bdb04a1e84d0455b3987e1fa9b83f322fc2df44acc8b7
+size 143153376

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b55169fe31e37a2e2dde32ccf2a2fdcd1cc7b30c0a06fd77dd13ffc4fa4fb97
+size 72886650

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b5fa4db2ec9f1dd83c22e31ef62ef4da0a2145da06b57bfd033599abd353ad
+size 14244

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d807bbd0c95f2d5fe6d3a34fd392cb32d62db708c74f56525909e7e3cc107e
+size 1064

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/special_tokens_map.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer.model

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/trainer_state.json

@@ -0,0 +1,2333 @@
+{
+  "best_metric": 1.238026738166809,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 3244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6662399081775104e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-3244/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+size 5560

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9786380ee461ab167b48ed45d7cab6fe7094739f47f6a289d7af4b8dbce5f32
+size 143153376

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b540c0bafda6b1b36ff3606a04dbc7c435a3c90649787c75efe0834bc6bfa2
+size 72886650

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e8376d55b7ad0f26d2ad80687f603a0e7227268397353a249ca7fb285073fa
+size 14244

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf44369560a6c20c2f557bcf58956ff63bc4bddae5bb9da652c28530e4c47b5
+size 1064

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/special_tokens_map.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer.model

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer_config.json

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