Upload folder using huggingface_hub

.gitattributes

@@ -2362,3 +2362,12 @@ gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1
 gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-1860-sd-42/checkpoint-812/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-1860-sd-42/checkpoint-928/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-1860-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-4/checkpoint-1827/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-4/checkpoint-2740/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-4/checkpoint-3654/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-4/checkpoint-4567/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-4/checkpoint-5481/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-4/checkpoint-6394/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-4/checkpoint-7304/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-4/checkpoint-913/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-4/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-4/README.md

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/adapter_config.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a867fb634fd8e3b066d1e5dba2fcd82385843220a23a334f7884c4c27c8b96
+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-4/checkpoint-1827/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-4/checkpoint-1827/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-4/checkpoint-1827/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a867fb634fd8e3b066d1e5dba2fcd82385843220a23a334f7884c4c27c8b96
+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-4/checkpoint-1827/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c65999d237dae4424b1944a70de5680c46f42713e3f2c8537a7c2ab85c5104
+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-4/checkpoint-1827/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e211764da55bdbda0c95564a513ca390fea4afa7b89981b7c84330cfeb75ce
+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-4/checkpoint-1827/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38841519e925109736ce493a81a32baf57374f07cc4493ecbc110955926f5fa2
+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-4/checkpoint-1827/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-4/checkpoint-1827/tokenizer.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/checkpoint-1827/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-4/checkpoint-1827/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-4/checkpoint-1827/trainer_state.json

@@ -0,0 +1,1323 @@
+{
+  "best_metric": 1.14472496509552,
+  "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-4/checkpoint-1827",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1827,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010946907498631636,
+      "grad_norm": 0.7611560821533203,
+      "learning_rate": 0.0002,
+      "loss": 2.4039,
+      "step": 10
+    },
+    {
+      "epoch": 0.021893814997263273,
+      "grad_norm": 0.4633193612098694,
+      "learning_rate": 0.0002,
+      "loss": 1.8818,
+      "step": 20
+    },
+    {
+      "epoch": 0.03284072249589491,
+      "grad_norm": 0.49326154589653015,
+      "learning_rate": 0.0002,
+      "loss": 1.5927,
+      "step": 30
+    },
+    {
+      "epoch": 0.043787629994526546,
+      "grad_norm": 0.3943138122558594,
+      "learning_rate": 0.0002,
+      "loss": 1.3859,
+      "step": 40
+    },
+    {
+      "epoch": 0.05473453749315818,
+      "grad_norm": 0.43292930722236633,
+      "learning_rate": 0.0002,
+      "loss": 1.3036,
+      "step": 50
+    },
+    {
+      "epoch": 0.06568144499178982,
+      "grad_norm": 0.3431817591190338,
+      "learning_rate": 0.0002,
+      "loss": 1.2427,
+      "step": 60
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.38011446595191956,
+      "learning_rate": 0.0002,
+      "loss": 1.3076,
+      "step": 70
+    },
+    {
+      "epoch": 0.08757525998905309,
+      "grad_norm": 0.7441071271896362,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 80
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.3359833061695099,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 90
+    },
+    {
+      "epoch": 0.10946907498631636,
+      "grad_norm": 0.3724392354488373,
+      "learning_rate": 0.0002,
+      "loss": 1.2774,
+      "step": 100
+    },
+    {
+      "epoch": 0.120415982484948,
+      "grad_norm": 0.40673762559890747,
+      "learning_rate": 0.0002,
+      "loss": 1.216,
+      "step": 110
+    },
+    {
+      "epoch": 0.13136288998357964,
+      "grad_norm": 0.40036800503730774,
+      "learning_rate": 0.0002,
+      "loss": 1.2611,
+      "step": 120
+    },
+    {
+      "epoch": 0.1423097974822113,
+      "grad_norm": 2.844191312789917,
+      "learning_rate": 0.0002,
+      "loss": 1.2436,
+      "step": 130
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.3104734420776367,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 140
+    },
+    {
+      "epoch": 0.16420361247947454,
+      "grad_norm": 0.3266797959804535,
+      "learning_rate": 0.0002,
+      "loss": 1.0498,
+      "step": 150
+    },
+    {
+      "epoch": 0.17515051997810618,
+      "grad_norm": 0.3079199194908142,
+      "learning_rate": 0.0002,
+      "loss": 1.1644,
+      "step": 160
+    },
+    {
+      "epoch": 0.18609742747673783,
+      "grad_norm": 0.3872479498386383,
+      "learning_rate": 0.0002,
+      "loss": 1.2923,
+      "step": 170
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.38654500246047974,
+      "learning_rate": 0.0002,
+      "loss": 1.1809,
+      "step": 180
+    },
+    {
+      "epoch": 0.20799124247400108,
+      "grad_norm": 0.2913552522659302,
+      "learning_rate": 0.0002,
+      "loss": 1.066,
+      "step": 190
+    },
+    {
+      "epoch": 0.21893814997263272,
+      "grad_norm": 0.2960572838783264,
+      "learning_rate": 0.0002,
+      "loss": 1.0868,
+      "step": 200
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.5175501108169556,
+      "learning_rate": 0.0002,
+      "loss": 1.136,
+      "step": 210
+    },
+    {
+      "epoch": 0.240831964969896,
+      "grad_norm": 1.2921574115753174,
+      "learning_rate": 0.0002,
+      "loss": 1.1556,
+      "step": 220
+    },
+    {
+      "epoch": 0.25177887246852765,
+      "grad_norm": 0.2675512135028839,
+      "learning_rate": 0.0002,
+      "loss": 1.1488,
+      "step": 230
+    },
+    {
+      "epoch": 0.2627257799671593,
+      "grad_norm": 0.3956190049648285,
+      "learning_rate": 0.0002,
+      "loss": 1.2764,
+      "step": 240
+    },
+    {
+      "epoch": 0.27367268746579093,
+      "grad_norm": 0.6022581458091736,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 250
+    },
+    {
+      "epoch": 0.2846195949644226,
+      "grad_norm": 1.1949563026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.1981,
+      "step": 260
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.31173548102378845,
+      "learning_rate": 0.0002,
+      "loss": 1.1877,
+      "step": 270
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2808472812175751,
+      "learning_rate": 0.0002,
+      "loss": 1.06,
+      "step": 280
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.3042023777961731,
+      "learning_rate": 0.0002,
+      "loss": 1.1752,
+      "step": 290
+    },
+    {
+      "epoch": 0.3284072249589491,
+      "grad_norm": 0.39915043115615845,
+      "learning_rate": 0.0002,
+      "loss": 1.3147,
+      "step": 300
+    },
+    {
+      "epoch": 0.3393541324575807,
+      "grad_norm": 0.39118197560310364,
+      "learning_rate": 0.0002,
+      "loss": 1.2425,
+      "step": 310
+    },
+    {
+      "epoch": 0.35030103995621237,
+      "grad_norm": 0.355010986328125,
+      "learning_rate": 0.0002,
+      "loss": 1.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.361247947454844,
+      "grad_norm": 0.29734086990356445,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 330
+    },
+    {
+      "epoch": 0.37219485495347565,
+      "grad_norm": 0.346096009016037,
+      "learning_rate": 0.0002,
+      "loss": 1.1974,
+      "step": 340
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.4829643666744232,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 350
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.4726872742176056,
+      "learning_rate": 0.0002,
+      "loss": 1.2808,
+      "step": 360
+    },
+    {
+      "epoch": 0.4050355774493706,
+      "grad_norm": 0.3130153715610504,
+      "learning_rate": 0.0002,
+      "loss": 1.1532,
+      "step": 370
+    },
+    {
+      "epoch": 0.41598248494800216,
+      "grad_norm": 0.5123590230941772,
+      "learning_rate": 0.0002,
+      "loss": 1.1842,
+      "step": 380
+    },
+    {
+      "epoch": 0.4269293924466338,
+      "grad_norm": 0.3444574773311615,
+      "learning_rate": 0.0002,
+      "loss": 1.1539,
+      "step": 390
+    },
+    {
+      "epoch": 0.43787629994526545,
+      "grad_norm": 0.5302175283432007,
+      "learning_rate": 0.0002,
+      "loss": 1.1756,
+      "step": 400
+    },
+    {
+      "epoch": 0.4488232074438971,
+      "grad_norm": 0.2713572680950165,
+      "learning_rate": 0.0002,
+      "loss": 1.1138,
+      "step": 410
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.29530611634254456,
+      "learning_rate": 0.0002,
+      "loss": 1.1281,
+      "step": 420
+    },
+    {
+      "epoch": 0.47071702244116037,
+      "grad_norm": 0.27282455563545227,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 430
+    },
+    {
+      "epoch": 0.481663929939792,
+      "grad_norm": 0.2647949755191803,
+      "learning_rate": 0.0002,
+      "loss": 1.1213,
+      "step": 440
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.35509347915649414,
+      "learning_rate": 0.0002,
+      "loss": 1.1656,
+      "step": 450
+    },
+    {
+      "epoch": 0.5035577449370553,
+      "grad_norm": 0.1959609091281891,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 460
+    },
+    {
+      "epoch": 0.5145046524356869,
+      "grad_norm": 0.40090155601501465,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 470
+    },
+    {
+      "epoch": 0.5254515599343186,
+      "grad_norm": 0.3354604244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.156,
+      "step": 480
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.2758506238460541,
+      "learning_rate": 0.0002,
+      "loss": 1.1024,
+      "step": 490
+    },
+    {
+      "epoch": 0.5473453749315819,
+      "grad_norm": 0.3629051744937897,
+      "learning_rate": 0.0002,
+      "loss": 1.1108,
+      "step": 500
+    },
+    {
+      "epoch": 0.5582922824302134,
+      "grad_norm": 0.30802229046821594,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 510
+    },
+    {
+      "epoch": 0.5692391899288451,
+      "grad_norm": 0.3099463880062103,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 520
+    },
+    {
+      "epoch": 0.5801860974274767,
+      "grad_norm": 0.42299067974090576,
+      "learning_rate": 0.0002,
+      "loss": 1.255,
+      "step": 530
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.5392252802848816,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 0.60207991242474,
+      "grad_norm": 0.34768250584602356,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 550
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.28490015864372253,
+      "learning_rate": 0.0002,
+      "loss": 1.102,
+      "step": 560
+    },
+    {
+      "epoch": 0.6239737274220033,
+      "grad_norm": 0.34787994623184204,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 570
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.29058772325515747,
+      "learning_rate": 0.0002,
+      "loss": 1.0759,
+      "step": 580
+    },
+    {
+      "epoch": 0.6458675424192666,
+      "grad_norm": 0.4063778817653656,
+      "learning_rate": 0.0002,
+      "loss": 1.1157,
+      "step": 590
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.9244267344474792,
+      "learning_rate": 0.0002,
+      "loss": 1.1432,
+      "step": 600
+    },
+    {
+      "epoch": 0.6677613574165299,
+      "grad_norm": 0.27605190873146057,
+      "learning_rate": 0.0002,
+      "loss": 1.0591,
+      "step": 610
+    },
+    {
+      "epoch": 0.6787082649151615,
+      "grad_norm": 0.34346821904182434,
+      "learning_rate": 0.0002,
+      "loss": 1.2123,
+      "step": 620
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.3093279302120209,
+      "learning_rate": 0.0002,
+      "loss": 1.2195,
+      "step": 630
+    },
+    {
+      "epoch": 0.7006020799124247,
+      "grad_norm": 1.0069009065628052,
+      "learning_rate": 0.0002,
+      "loss": 1.2461,
+      "step": 640
+    },
+    {
+      "epoch": 0.7115489874110563,
+      "grad_norm": 0.5049130916595459,
+      "learning_rate": 0.0002,
+      "loss": 1.0892,
+      "step": 650
+    },
+    {
+      "epoch": 0.722495894909688,
+      "grad_norm": 0.3748924732208252,
+      "learning_rate": 0.0002,
+      "loss": 1.1404,
+      "step": 660
+    },
+    {
+      "epoch": 0.7334428024083196,
+      "grad_norm": 0.2964959144592285,
+      "learning_rate": 0.0002,
+      "loss": 1.1062,
+      "step": 670
+    },
+    {
+      "epoch": 0.7443897099069513,
+      "grad_norm": 0.4599986970424652,
+      "learning_rate": 0.0002,
+      "loss": 1.2617,
+      "step": 680
+    },
+    {
+      "epoch": 0.7553366174055829,
+      "grad_norm": 0.27292951941490173,
+      "learning_rate": 0.0002,
+      "loss": 1.088,
+      "step": 690
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.3123566806316376,
+      "learning_rate": 0.0002,
+      "loss": 1.2047,
+      "step": 700
+    },
+    {
+      "epoch": 0.7772304324028462,
+      "grad_norm": 0.28310710191726685,
+      "learning_rate": 0.0002,
+      "loss": 1.0021,
+      "step": 710
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.3279992341995239,
+      "learning_rate": 0.0002,
+      "loss": 1.2281,
+      "step": 720
+    },
+    {
+      "epoch": 0.7991242474001095,
+      "grad_norm": 0.28179168701171875,
+      "learning_rate": 0.0002,
+      "loss": 1.25,
+      "step": 730
+    },
+    {
+      "epoch": 0.8100711548987412,
+      "grad_norm": 0.31492987275123596,
+      "learning_rate": 0.0002,
+      "loss": 1.0602,
+      "step": 740
+    },
+    {
+      "epoch": 0.8210180623973727,
+      "grad_norm": 0.41821011900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.2518,
+      "step": 750
+    },
+    {
+      "epoch": 0.8319649698960043,
+      "grad_norm": 0.325235515832901,
+      "learning_rate": 0.0002,
+      "loss": 1.1612,
+      "step": 760
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.5366070866584778,
+      "learning_rate": 0.0002,
+      "loss": 1.27,
+      "step": 770
+    },
+    {
+      "epoch": 0.8538587848932676,
+      "grad_norm": 0.32570579648017883,
+      "learning_rate": 0.0002,
+      "loss": 1.0921,
+      "step": 780
+    },
+    {
+      "epoch": 0.8648056923918993,
+      "grad_norm": 0.3642968237400055,
+      "learning_rate": 0.0002,
+      "loss": 1.1032,
+      "step": 790
+    },
+    {
+      "epoch": 0.8757525998905309,
+      "grad_norm": 0.29713448882102966,
+      "learning_rate": 0.0002,
+      "loss": 1.1234,
+      "step": 800
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.23599444329738617,
+      "learning_rate": 0.0002,
+      "loss": 1.0978,
+      "step": 810
+    },
+    {
+      "epoch": 0.8976464148877942,
+      "grad_norm": 0.31522464752197266,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 820
+    },
+    {
+      "epoch": 0.9085933223864259,
+      "grad_norm": 0.32754790782928467,
+      "learning_rate": 0.0002,
+      "loss": 1.0208,
+      "step": 830
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22741089761257172,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 840
+    },
+    {
+      "epoch": 0.9304871373836892,
+      "grad_norm": 0.3089679777622223,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 850
+    },
+    {
+      "epoch": 0.9414340448823207,
+      "grad_norm": 0.27440521121025085,
+      "learning_rate": 0.0002,
+      "loss": 1.0354,
+      "step": 860
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3498363792896271,
+      "learning_rate": 0.0002,
+      "loss": 1.0417,
+      "step": 870
+    },
+    {
+      "epoch": 0.963327859879584,
+      "grad_norm": 0.47151854634284973,
+      "learning_rate": 0.0002,
+      "loss": 1.269,
+      "step": 880
+    },
+    {
+      "epoch": 0.9742747673782156,
+      "grad_norm": 0.24756591022014618,
+      "learning_rate": 0.0002,
+      "loss": 1.1174,
+      "step": 890
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.2600938677787781,
+      "learning_rate": 0.0002,
+      "loss": 1.0622,
+      "step": 900
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.2934586703777313,
+      "learning_rate": 0.0002,
+      "loss": 1.0968,
+      "step": 910
+    },
+    {
+      "epoch": 0.9994526546250684,
+      "eval_loss": 1.158464789390564,
+      "eval_runtime": 46.0774,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 913
+    },
+    {
+      "epoch": 1.0071154898741106,
+      "grad_norm": 0.37776654958724976,
+      "learning_rate": 0.0002,
+      "loss": 1.0322,
+      "step": 920
+    },
+    {
+      "epoch": 1.0180623973727423,
+      "grad_norm": 0.31784629821777344,
+      "learning_rate": 0.0002,
+      "loss": 1.1346,
+      "step": 930
+    },
+    {
+      "epoch": 1.0290093048713738,
+      "grad_norm": 0.24244336783885956,
+      "learning_rate": 0.0002,
+      "loss": 0.8976,
+      "step": 940
+    },
+    {
+      "epoch": 1.0399562123700055,
+      "grad_norm": 0.3185454308986664,
+      "learning_rate": 0.0002,
+      "loss": 1.0172,
+      "step": 950
+    },
+    {
+      "epoch": 1.0509031198686372,
+      "grad_norm": 0.3589441478252411,
+      "learning_rate": 0.0002,
+      "loss": 1.1645,
+      "step": 960
+    },
+    {
+      "epoch": 1.0618500273672686,
+      "grad_norm": 0.38593578338623047,
+      "learning_rate": 0.0002,
+      "loss": 1.0317,
+      "step": 970
+    },
+    {
+      "epoch": 1.0727969348659003,
+      "grad_norm": 0.39694955945014954,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 980
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.469817191362381,
+      "learning_rate": 0.0002,
+      "loss": 1.0893,
+      "step": 990
+    },
+    {
+      "epoch": 1.0946907498631637,
+      "grad_norm": 0.2634755074977875,
+      "learning_rate": 0.0002,
+      "loss": 0.983,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1056376573617952,
+      "grad_norm": 0.43189436197280884,
+      "learning_rate": 0.0002,
+      "loss": 1.0144,
+      "step": 1010
+    },
+    {
+      "epoch": 1.116584564860427,
+      "grad_norm": 0.5559977889060974,
+      "learning_rate": 0.0002,
+      "loss": 0.9663,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1275314723590586,
+      "grad_norm": 0.32100191712379456,
+      "learning_rate": 0.0002,
+      "loss": 1.0481,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1384783798576903,
+      "grad_norm": 0.40179768204689026,
+      "learning_rate": 0.0002,
+      "loss": 1.1012,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.3659493029117584,
+      "learning_rate": 0.0002,
+      "loss": 1.0029,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1603721948549535,
+      "grad_norm": 0.701704204082489,
+      "learning_rate": 0.0002,
+      "loss": 0.9597,
+      "step": 1060
+    },
+    {
+      "epoch": 1.1713191023535852,
+      "grad_norm": 0.3650563359260559,
+      "learning_rate": 0.0002,
+      "loss": 1.0204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.3191976249217987,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1080
+    },
+    {
+      "epoch": 1.1932129173508483,
+      "grad_norm": 0.3615441918373108,
+      "learning_rate": 0.0002,
+      "loss": 1.0648,
+      "step": 1090
+    },
+    {
+      "epoch": 1.20415982484948,
+      "grad_norm": 0.39474231004714966,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2151067323481117,
+      "grad_norm": 0.3752822279930115,
+      "learning_rate": 0.0002,
+      "loss": 0.9852,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2260536398467432,
+      "grad_norm": 0.4165991246700287,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1120
+    },
+    {
+      "epoch": 1.237000547345375,
+      "grad_norm": 0.5326506495475769,
+      "learning_rate": 0.0002,
+      "loss": 1.0244,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2479474548440066,
+      "grad_norm": 0.48845794796943665,
+      "learning_rate": 0.0002,
+      "loss": 1.0542,
+      "step": 1140
+    },
+    {
+      "epoch": 1.2588943623426383,
+      "grad_norm": 0.29910150170326233,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.5069725513458252,
+      "learning_rate": 0.0002,
+      "loss": 1.2233,
+      "step": 1160
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 0.29500406980514526,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 1170
+    },
+    {
+      "epoch": 1.2917350848385332,
+      "grad_norm": 0.4711538851261139,
+      "learning_rate": 0.0002,
+      "loss": 1.0291,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3026819923371646,
+      "grad_norm": 0.4203340709209442,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1190
+    },
+    {
+      "epoch": 1.3136288998357963,
+      "grad_norm": 0.36101874709129333,
+      "learning_rate": 0.0002,
+      "loss": 1.1274,
+      "step": 1200
+    },
+    {
+      "epoch": 1.324575807334428,
+      "grad_norm": 0.4608800411224365,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 1210
+    },
+    {
+      "epoch": 1.3355227148330597,
+      "grad_norm": 0.6570906639099121,
+      "learning_rate": 0.0002,
+      "loss": 1.0695,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3464696223316914,
+      "grad_norm": 0.5352164506912231,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 1230
+    },
+    {
+      "epoch": 1.357416529830323,
+      "grad_norm": 0.3885001242160797,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1240
+    },
+    {
+      "epoch": 1.3683634373289546,
+      "grad_norm": 0.2987913489341736,
+      "learning_rate": 0.0002,
+      "loss": 1.0611,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.42070427536964417,
+      "learning_rate": 0.0002,
+      "loss": 1.109,
+      "step": 1260
+    },
+    {
+      "epoch": 1.3902572523262178,
+      "grad_norm": 0.5957782864570618,
+      "learning_rate": 0.0002,
+      "loss": 1.1092,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4012041598248495,
+      "grad_norm": 0.32898882031440735,
+      "learning_rate": 0.0002,
+      "loss": 1.0554,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4121510673234812,
+      "grad_norm": 0.27624452114105225,
+      "learning_rate": 0.0002,
+      "loss": 0.909,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4230979748221126,
+      "grad_norm": 0.49570828676223755,
+      "learning_rate": 0.0002,
+      "loss": 1.024,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4340448823207443,
+      "grad_norm": 0.26191383600234985,
+      "learning_rate": 0.0002,
+      "loss": 1.0471,
+      "step": 1310
+    },
+    {
+      "epoch": 1.444991789819376,
+      "grad_norm": 0.35664042830467224,
+      "learning_rate": 0.0002,
+      "loss": 1.0788,
+      "step": 1320
+    },
+    {
+      "epoch": 1.4559386973180077,
+      "grad_norm": 0.45126354694366455,
+      "learning_rate": 0.0002,
+      "loss": 1.0108,
+      "step": 1330
+    },
+    {
+      "epoch": 1.4668856048166394,
+      "grad_norm": 0.37318357825279236,
+      "learning_rate": 0.0002,
+      "loss": 0.9571,
+      "step": 1340
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 0.6428970098495483,
+      "learning_rate": 0.0002,
+      "loss": 1.0507,
+      "step": 1350
+    },
+    {
+      "epoch": 1.4887794198139026,
+      "grad_norm": 0.43256187438964844,
+      "learning_rate": 0.0002,
+      "loss": 1.0367,
+      "step": 1360
+    },
+    {
+      "epoch": 1.4997263273125343,
+      "grad_norm": 0.5343793630599976,
+      "learning_rate": 0.0002,
+      "loss": 1.1321,
+      "step": 1370
+    },
+    {
+      "epoch": 1.5106732348111658,
+      "grad_norm": 0.315437376499176,
+      "learning_rate": 0.0002,
+      "loss": 1.1054,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5216201423097975,
+      "grad_norm": 0.41561153531074524,
+      "learning_rate": 0.0002,
+      "loss": 0.8916,
+      "step": 1390
+    },
+    {
+      "epoch": 1.5325670498084292,
+      "grad_norm": 0.3201070725917816,
+      "learning_rate": 0.0002,
+      "loss": 1.0391,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5435139573070606,
+      "grad_norm": 0.505537211894989,
+      "learning_rate": 0.0002,
+      "loss": 1.14,
+      "step": 1410
+    },
+    {
+      "epoch": 1.5544608648056923,
+      "grad_norm": 0.3747410178184509,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 1420
+    },
+    {
+      "epoch": 1.565407772304324,
+      "grad_norm": 0.49385908246040344,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 1430
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 0.49831628799438477,
+      "learning_rate": 0.0002,
+      "loss": 1.1182,
+      "step": 1440
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.372127890586853,
+      "learning_rate": 0.0002,
+      "loss": 1.0079,
+      "step": 1450
+    },
+    {
+      "epoch": 1.598248494800219,
+      "grad_norm": 0.40070840716362,
+      "learning_rate": 0.0002,
+      "loss": 0.9931,
+      "step": 1460
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.34907400608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6201423097974823,
+      "grad_norm": 0.4632418751716614,
+      "learning_rate": 0.0002,
+      "loss": 0.9743,
+      "step": 1480
+    },
+    {
+      "epoch": 1.6310892172961138,
+      "grad_norm": 0.40164515376091003,
+      "learning_rate": 0.0002,
+      "loss": 1.0103,
+      "step": 1490
+    },
+    {
+      "epoch": 1.6420361247947455,
+      "grad_norm": 0.3214994966983795,
+      "learning_rate": 0.0002,
+      "loss": 0.9523,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6529830322933772,
+      "grad_norm": 0.3727897107601166,
+      "learning_rate": 0.0002,
+      "loss": 1.0161,
+      "step": 1510
+    },
+    {
+      "epoch": 1.6639299397920086,
+      "grad_norm": 0.3817640542984009,
+      "learning_rate": 0.0002,
+      "loss": 1.0443,
+      "step": 1520
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.5592136979103088,
+      "learning_rate": 0.0002,
+      "loss": 1.0511,
+      "step": 1530
+    },
+    {
+      "epoch": 1.685823754789272,
+      "grad_norm": 0.44636598229408264,
+      "learning_rate": 0.0002,
+      "loss": 0.9682,
+      "step": 1540
+    },
+    {
+      "epoch": 1.6967706622879035,
+      "grad_norm": 0.40441709756851196,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7077175697865354,
+      "grad_norm": 0.3243522644042969,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1560
+    },
+    {
+      "epoch": 1.718664477285167,
+      "grad_norm": 0.34277570247650146,
+      "learning_rate": 0.0002,
+      "loss": 0.9482,
+      "step": 1570
+    },
+    {
+      "epoch": 1.7296113847837986,
+      "grad_norm": 0.3279995024204254,
+      "learning_rate": 0.0002,
+      "loss": 0.974,
+      "step": 1580
+    },
+    {
+      "epoch": 1.7405582922824303,
+      "grad_norm": 0.41968777775764465,
+      "learning_rate": 0.0002,
+      "loss": 0.9414,
+      "step": 1590
+    },
+    {
+      "epoch": 1.7515051997810618,
+      "grad_norm": 0.39464613795280457,
+      "learning_rate": 0.0002,
+      "loss": 0.9768,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7624521072796935,
+      "grad_norm": 0.3839009404182434,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 1610
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 0.3250715434551239,
+      "learning_rate": 0.0002,
+      "loss": 0.9195,
+      "step": 1620
+    },
+    {
+      "epoch": 1.7843459222769567,
+      "grad_norm": 0.5166561007499695,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 1630
+    },
+    {
+      "epoch": 1.7952928297755884,
+      "grad_norm": 0.4115183353424072,
+      "learning_rate": 0.0002,
+      "loss": 1.0364,
+      "step": 1640
+    },
+    {
+      "epoch": 1.80623973727422,
+      "grad_norm": 0.373780220746994,
+      "learning_rate": 0.0002,
+      "loss": 1.0248,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8171866447728515,
+      "grad_norm": 0.49697014689445496,
+      "learning_rate": 0.0002,
+      "loss": 1.0984,
+      "step": 1660
+    },
+    {
+      "epoch": 1.8281335522714834,
+      "grad_norm": 1.0308938026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.0089,
+      "step": 1670
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.4851366877555847,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 1680
+    },
+    {
+      "epoch": 1.8500273672687466,
+      "grad_norm": 0.3262481391429901,
+      "learning_rate": 0.0002,
+      "loss": 0.9533,
+      "step": 1690
+    },
+    {
+      "epoch": 1.8609742747673783,
+      "grad_norm": 0.6904496550559998,
+      "learning_rate": 0.0002,
+      "loss": 1.048,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 0.49789851903915405,
+      "learning_rate": 0.0002,
+      "loss": 1.0577,
+      "step": 1710
+    },
+    {
+      "epoch": 1.8828680897646415,
+      "grad_norm": 0.3035794198513031,
+      "learning_rate": 0.0002,
+      "loss": 1.0258,
+      "step": 1720
+    },
+    {
+      "epoch": 1.8938149972632732,
+      "grad_norm": 0.4588414430618286,
+      "learning_rate": 0.0002,
+      "loss": 0.9916,
+      "step": 1730
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.4313034117221832,
+      "learning_rate": 0.0002,
+      "loss": 0.9526,
+      "step": 1740
+    },
+    {
+      "epoch": 1.9157088122605364,
+      "grad_norm": 0.38562044501304626,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1750
+    },
+    {
+      "epoch": 1.926655719759168,
+      "grad_norm": 0.46947410702705383,
+      "learning_rate": 0.0002,
+      "loss": 0.9763,
+      "step": 1760
+    },
+    {
+      "epoch": 1.9376026272577995,
+      "grad_norm": 0.3848404884338379,
+      "learning_rate": 0.0002,
+      "loss": 0.9967,
+      "step": 1770
+    },
+    {
+      "epoch": 1.9485495347564314,
+      "grad_norm": 0.30422744154930115,
+      "learning_rate": 0.0002,
+      "loss": 1.0474,
+      "step": 1780
+    },
+    {
+      "epoch": 1.959496442255063,
+      "grad_norm": 0.41100990772247314,
+      "learning_rate": 0.0002,
+      "loss": 1.022,
+      "step": 1790
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 0.3492335081100464,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9813902572523263,
+      "grad_norm": 0.364577978849411,
+      "learning_rate": 0.0002,
+      "loss": 0.9891,
+      "step": 1810
+    },
+    {
+      "epoch": 1.9923371647509578,
+      "grad_norm": 0.4312075674533844,
+      "learning_rate": 0.0002,
+      "loss": 1.0699,
+      "step": 1820
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.14472496509552,
+      "eval_runtime": 46.0786,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 1827
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7304,
+  "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": 9.384156326264832e+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-4/checkpoint-1827/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a158bca77bc6d58bfffd2acd2e9e641d481e1857fcbdd68fee875b74797abbc4
+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-4/checkpoint-2740/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-4/checkpoint-2740/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-4/checkpoint-2740/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035921963b7ba3426c7b25b29c3e4e62d3764d0ef3b24abb0b53606c314dc350
+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-4/checkpoint-2740/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d210241b2fbe25b1e819460216e4143f1484c8e6fc3636c95d1498e9b095ca51
+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-4/checkpoint-2740/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf917d2e89ee39a3e9cdfb5c9be783c7806b020f29415fe37710fbbf43833346
+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-4/checkpoint-2740/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c054e94e5454455e09f8cd2be3390222c38c11f62f45d2b0a3f8280bdbc1c254
+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-4/checkpoint-2740/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-4/checkpoint-2740/tokenizer.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/checkpoint-2740/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-4/checkpoint-2740/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-4/checkpoint-2740/trainer_state.json

@@ -0,0 +1,1975 @@
+{
+  "best_metric": 1.14472496509552,
+  "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-4/checkpoint-1827",
+  "epoch": 2.9994526546250686,
+  "eval_steps": 10,
+  "global_step": 2740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010946907498631636,
+      "grad_norm": 0.7611560821533203,
+      "learning_rate": 0.0002,
+      "loss": 2.4039,
+      "step": 10
+    },
+    {
+      "epoch": 0.021893814997263273,
+      "grad_norm": 0.4633193612098694,
+      "learning_rate": 0.0002,
+      "loss": 1.8818,
+      "step": 20
+    },
+    {
+      "epoch": 0.03284072249589491,
+      "grad_norm": 0.49326154589653015,
+      "learning_rate": 0.0002,
+      "loss": 1.5927,
+      "step": 30
+    },
+    {
+      "epoch": 0.043787629994526546,
+      "grad_norm": 0.3943138122558594,
+      "learning_rate": 0.0002,
+      "loss": 1.3859,
+      "step": 40
+    },
+    {
+      "epoch": 0.05473453749315818,
+      "grad_norm": 0.43292930722236633,
+      "learning_rate": 0.0002,
+      "loss": 1.3036,
+      "step": 50
+    },
+    {
+      "epoch": 0.06568144499178982,
+      "grad_norm": 0.3431817591190338,
+      "learning_rate": 0.0002,
+      "loss": 1.2427,
+      "step": 60
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.38011446595191956,
+      "learning_rate": 0.0002,
+      "loss": 1.3076,
+      "step": 70
+    },
+    {
+      "epoch": 0.08757525998905309,
+      "grad_norm": 0.7441071271896362,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 80
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.3359833061695099,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 90
+    },
+    {
+      "epoch": 0.10946907498631636,
+      "grad_norm": 0.3724392354488373,
+      "learning_rate": 0.0002,
+      "loss": 1.2774,
+      "step": 100
+    },
+    {
+      "epoch": 0.120415982484948,
+      "grad_norm": 0.40673762559890747,
+      "learning_rate": 0.0002,
+      "loss": 1.216,
+      "step": 110
+    },
+    {
+      "epoch": 0.13136288998357964,
+      "grad_norm": 0.40036800503730774,
+      "learning_rate": 0.0002,
+      "loss": 1.2611,
+      "step": 120
+    },
+    {
+      "epoch": 0.1423097974822113,
+      "grad_norm": 2.844191312789917,
+      "learning_rate": 0.0002,
+      "loss": 1.2436,
+      "step": 130
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.3104734420776367,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 140
+    },
+    {
+      "epoch": 0.16420361247947454,
+      "grad_norm": 0.3266797959804535,
+      "learning_rate": 0.0002,
+      "loss": 1.0498,
+      "step": 150
+    },
+    {
+      "epoch": 0.17515051997810618,
+      "grad_norm": 0.3079199194908142,
+      "learning_rate": 0.0002,
+      "loss": 1.1644,
+      "step": 160
+    },
+    {
+      "epoch": 0.18609742747673783,
+      "grad_norm": 0.3872479498386383,
+      "learning_rate": 0.0002,
+      "loss": 1.2923,
+      "step": 170
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.38654500246047974,
+      "learning_rate": 0.0002,
+      "loss": 1.1809,
+      "step": 180
+    },
+    {
+      "epoch": 0.20799124247400108,
+      "grad_norm": 0.2913552522659302,
+      "learning_rate": 0.0002,
+      "loss": 1.066,
+      "step": 190
+    },
+    {
+      "epoch": 0.21893814997263272,
+      "grad_norm": 0.2960572838783264,
+      "learning_rate": 0.0002,
+      "loss": 1.0868,
+      "step": 200
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.5175501108169556,
+      "learning_rate": 0.0002,
+      "loss": 1.136,
+      "step": 210
+    },
+    {
+      "epoch": 0.240831964969896,
+      "grad_norm": 1.2921574115753174,
+      "learning_rate": 0.0002,
+      "loss": 1.1556,
+      "step": 220
+    },
+    {
+      "epoch": 0.25177887246852765,
+      "grad_norm": 0.2675512135028839,
+      "learning_rate": 0.0002,
+      "loss": 1.1488,
+      "step": 230
+    },
+    {
+      "epoch": 0.2627257799671593,
+      "grad_norm": 0.3956190049648285,
+      "learning_rate": 0.0002,
+      "loss": 1.2764,
+      "step": 240
+    },
+    {
+      "epoch": 0.27367268746579093,
+      "grad_norm": 0.6022581458091736,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 250
+    },
+    {
+      "epoch": 0.2846195949644226,
+      "grad_norm": 1.1949563026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.1981,
+      "step": 260
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.31173548102378845,
+      "learning_rate": 0.0002,
+      "loss": 1.1877,
+      "step": 270
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2808472812175751,
+      "learning_rate": 0.0002,
+      "loss": 1.06,
+      "step": 280
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.3042023777961731,
+      "learning_rate": 0.0002,
+      "loss": 1.1752,
+      "step": 290
+    },
+    {
+      "epoch": 0.3284072249589491,
+      "grad_norm": 0.39915043115615845,
+      "learning_rate": 0.0002,
+      "loss": 1.3147,
+      "step": 300
+    },
+    {
+      "epoch": 0.3393541324575807,
+      "grad_norm": 0.39118197560310364,
+      "learning_rate": 0.0002,
+      "loss": 1.2425,
+      "step": 310
+    },
+    {
+      "epoch": 0.35030103995621237,
+      "grad_norm": 0.355010986328125,
+      "learning_rate": 0.0002,
+      "loss": 1.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.361247947454844,
+      "grad_norm": 0.29734086990356445,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 330
+    },
+    {
+      "epoch": 0.37219485495347565,
+      "grad_norm": 0.346096009016037,
+      "learning_rate": 0.0002,
+      "loss": 1.1974,
+      "step": 340
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.4829643666744232,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 350
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.4726872742176056,
+      "learning_rate": 0.0002,
+      "loss": 1.2808,
+      "step": 360
+    },
+    {
+      "epoch": 0.4050355774493706,
+      "grad_norm": 0.3130153715610504,
+      "learning_rate": 0.0002,
+      "loss": 1.1532,
+      "step": 370
+    },
+    {
+      "epoch": 0.41598248494800216,
+      "grad_norm": 0.5123590230941772,
+      "learning_rate": 0.0002,
+      "loss": 1.1842,
+      "step": 380
+    },
+    {
+      "epoch": 0.4269293924466338,
+      "grad_norm": 0.3444574773311615,
+      "learning_rate": 0.0002,
+      "loss": 1.1539,
+      "step": 390
+    },
+    {
+      "epoch": 0.43787629994526545,
+      "grad_norm": 0.5302175283432007,
+      "learning_rate": 0.0002,
+      "loss": 1.1756,
+      "step": 400
+    },
+    {
+      "epoch": 0.4488232074438971,
+      "grad_norm": 0.2713572680950165,
+      "learning_rate": 0.0002,
+      "loss": 1.1138,
+      "step": 410
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.29530611634254456,
+      "learning_rate": 0.0002,
+      "loss": 1.1281,
+      "step": 420
+    },
+    {
+      "epoch": 0.47071702244116037,
+      "grad_norm": 0.27282455563545227,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 430
+    },
+    {
+      "epoch": 0.481663929939792,
+      "grad_norm": 0.2647949755191803,
+      "learning_rate": 0.0002,
+      "loss": 1.1213,
+      "step": 440
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.35509347915649414,
+      "learning_rate": 0.0002,
+      "loss": 1.1656,
+      "step": 450
+    },
+    {
+      "epoch": 0.5035577449370553,
+      "grad_norm": 0.1959609091281891,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 460
+    },
+    {
+      "epoch": 0.5145046524356869,
+      "grad_norm": 0.40090155601501465,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 470
+    },
+    {
+      "epoch": 0.5254515599343186,
+      "grad_norm": 0.3354604244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.156,
+      "step": 480
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.2758506238460541,
+      "learning_rate": 0.0002,
+      "loss": 1.1024,
+      "step": 490
+    },
+    {
+      "epoch": 0.5473453749315819,
+      "grad_norm": 0.3629051744937897,
+      "learning_rate": 0.0002,
+      "loss": 1.1108,
+      "step": 500
+    },
+    {
+      "epoch": 0.5582922824302134,
+      "grad_norm": 0.30802229046821594,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 510
+    },
+    {
+      "epoch": 0.5692391899288451,
+      "grad_norm": 0.3099463880062103,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 520
+    },
+    {
+      "epoch": 0.5801860974274767,
+      "grad_norm": 0.42299067974090576,
+      "learning_rate": 0.0002,
+      "loss": 1.255,
+      "step": 530
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.5392252802848816,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 0.60207991242474,
+      "grad_norm": 0.34768250584602356,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 550
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.28490015864372253,
+      "learning_rate": 0.0002,
+      "loss": 1.102,
+      "step": 560
+    },
+    {
+      "epoch": 0.6239737274220033,
+      "grad_norm": 0.34787994623184204,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 570
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.29058772325515747,
+      "learning_rate": 0.0002,
+      "loss": 1.0759,
+      "step": 580
+    },
+    {
+      "epoch": 0.6458675424192666,
+      "grad_norm": 0.4063778817653656,
+      "learning_rate": 0.0002,
+      "loss": 1.1157,
+      "step": 590
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.9244267344474792,
+      "learning_rate": 0.0002,
+      "loss": 1.1432,
+      "step": 600
+    },
+    {
+      "epoch": 0.6677613574165299,
+      "grad_norm": 0.27605190873146057,
+      "learning_rate": 0.0002,
+      "loss": 1.0591,
+      "step": 610
+    },
+    {
+      "epoch": 0.6787082649151615,
+      "grad_norm": 0.34346821904182434,
+      "learning_rate": 0.0002,
+      "loss": 1.2123,
+      "step": 620
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.3093279302120209,
+      "learning_rate": 0.0002,
+      "loss": 1.2195,
+      "step": 630
+    },
+    {
+      "epoch": 0.7006020799124247,
+      "grad_norm": 1.0069009065628052,
+      "learning_rate": 0.0002,
+      "loss": 1.2461,
+      "step": 640
+    },
+    {
+      "epoch": 0.7115489874110563,
+      "grad_norm": 0.5049130916595459,
+      "learning_rate": 0.0002,
+      "loss": 1.0892,
+      "step": 650
+    },
+    {
+      "epoch": 0.722495894909688,
+      "grad_norm": 0.3748924732208252,
+      "learning_rate": 0.0002,
+      "loss": 1.1404,
+      "step": 660
+    },
+    {
+      "epoch": 0.7334428024083196,
+      "grad_norm": 0.2964959144592285,
+      "learning_rate": 0.0002,
+      "loss": 1.1062,
+      "step": 670
+    },
+    {
+      "epoch": 0.7443897099069513,
+      "grad_norm": 0.4599986970424652,
+      "learning_rate": 0.0002,
+      "loss": 1.2617,
+      "step": 680
+    },
+    {
+      "epoch": 0.7553366174055829,
+      "grad_norm": 0.27292951941490173,
+      "learning_rate": 0.0002,
+      "loss": 1.088,
+      "step": 690
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.3123566806316376,
+      "learning_rate": 0.0002,
+      "loss": 1.2047,
+      "step": 700
+    },
+    {
+      "epoch": 0.7772304324028462,
+      "grad_norm": 0.28310710191726685,
+      "learning_rate": 0.0002,
+      "loss": 1.0021,
+      "step": 710
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.3279992341995239,
+      "learning_rate": 0.0002,
+      "loss": 1.2281,
+      "step": 720
+    },
+    {
+      "epoch": 0.7991242474001095,
+      "grad_norm": 0.28179168701171875,
+      "learning_rate": 0.0002,
+      "loss": 1.25,
+      "step": 730
+    },
+    {
+      "epoch": 0.8100711548987412,
+      "grad_norm": 0.31492987275123596,
+      "learning_rate": 0.0002,
+      "loss": 1.0602,
+      "step": 740
+    },
+    {
+      "epoch": 0.8210180623973727,
+      "grad_norm": 0.41821011900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.2518,
+      "step": 750
+    },
+    {
+      "epoch": 0.8319649698960043,
+      "grad_norm": 0.325235515832901,
+      "learning_rate": 0.0002,
+      "loss": 1.1612,
+      "step": 760
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.5366070866584778,
+      "learning_rate": 0.0002,
+      "loss": 1.27,
+      "step": 770
+    },
+    {
+      "epoch": 0.8538587848932676,
+      "grad_norm": 0.32570579648017883,
+      "learning_rate": 0.0002,
+      "loss": 1.0921,
+      "step": 780
+    },
+    {
+      "epoch": 0.8648056923918993,
+      "grad_norm": 0.3642968237400055,
+      "learning_rate": 0.0002,
+      "loss": 1.1032,
+      "step": 790
+    },
+    {
+      "epoch": 0.8757525998905309,
+      "grad_norm": 0.29713448882102966,
+      "learning_rate": 0.0002,
+      "loss": 1.1234,
+      "step": 800
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.23599444329738617,
+      "learning_rate": 0.0002,
+      "loss": 1.0978,
+      "step": 810
+    },
+    {
+      "epoch": 0.8976464148877942,
+      "grad_norm": 0.31522464752197266,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 820
+    },
+    {
+      "epoch": 0.9085933223864259,
+      "grad_norm": 0.32754790782928467,
+      "learning_rate": 0.0002,
+      "loss": 1.0208,
+      "step": 830
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22741089761257172,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 840
+    },
+    {
+      "epoch": 0.9304871373836892,
+      "grad_norm": 0.3089679777622223,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 850
+    },
+    {
+      "epoch": 0.9414340448823207,
+      "grad_norm": 0.27440521121025085,
+      "learning_rate": 0.0002,
+      "loss": 1.0354,
+      "step": 860
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3498363792896271,
+      "learning_rate": 0.0002,
+      "loss": 1.0417,
+      "step": 870
+    },
+    {
+      "epoch": 0.963327859879584,
+      "grad_norm": 0.47151854634284973,
+      "learning_rate": 0.0002,
+      "loss": 1.269,
+      "step": 880
+    },
+    {
+      "epoch": 0.9742747673782156,
+      "grad_norm": 0.24756591022014618,
+      "learning_rate": 0.0002,
+      "loss": 1.1174,
+      "step": 890
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.2600938677787781,
+      "learning_rate": 0.0002,
+      "loss": 1.0622,
+      "step": 900
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.2934586703777313,
+      "learning_rate": 0.0002,
+      "loss": 1.0968,
+      "step": 910
+    },
+    {
+      "epoch": 0.9994526546250684,
+      "eval_loss": 1.158464789390564,
+      "eval_runtime": 46.0774,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 913
+    },
+    {
+      "epoch": 1.0071154898741106,
+      "grad_norm": 0.37776654958724976,
+      "learning_rate": 0.0002,
+      "loss": 1.0322,
+      "step": 920
+    },
+    {
+      "epoch": 1.0180623973727423,
+      "grad_norm": 0.31784629821777344,
+      "learning_rate": 0.0002,
+      "loss": 1.1346,
+      "step": 930
+    },
+    {
+      "epoch": 1.0290093048713738,
+      "grad_norm": 0.24244336783885956,
+      "learning_rate": 0.0002,
+      "loss": 0.8976,
+      "step": 940
+    },
+    {
+      "epoch": 1.0399562123700055,
+      "grad_norm": 0.3185454308986664,
+      "learning_rate": 0.0002,
+      "loss": 1.0172,
+      "step": 950
+    },
+    {
+      "epoch": 1.0509031198686372,
+      "grad_norm": 0.3589441478252411,
+      "learning_rate": 0.0002,
+      "loss": 1.1645,
+      "step": 960
+    },
+    {
+      "epoch": 1.0618500273672686,
+      "grad_norm": 0.38593578338623047,
+      "learning_rate": 0.0002,
+      "loss": 1.0317,
+      "step": 970
+    },
+    {
+      "epoch": 1.0727969348659003,
+      "grad_norm": 0.39694955945014954,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 980
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.469817191362381,
+      "learning_rate": 0.0002,
+      "loss": 1.0893,
+      "step": 990
+    },
+    {
+      "epoch": 1.0946907498631637,
+      "grad_norm": 0.2634755074977875,
+      "learning_rate": 0.0002,
+      "loss": 0.983,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1056376573617952,
+      "grad_norm": 0.43189436197280884,
+      "learning_rate": 0.0002,
+      "loss": 1.0144,
+      "step": 1010
+    },
+    {
+      "epoch": 1.116584564860427,
+      "grad_norm": 0.5559977889060974,
+      "learning_rate": 0.0002,
+      "loss": 0.9663,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1275314723590586,
+      "grad_norm": 0.32100191712379456,
+      "learning_rate": 0.0002,
+      "loss": 1.0481,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1384783798576903,
+      "grad_norm": 0.40179768204689026,
+      "learning_rate": 0.0002,
+      "loss": 1.1012,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.3659493029117584,
+      "learning_rate": 0.0002,
+      "loss": 1.0029,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1603721948549535,
+      "grad_norm": 0.701704204082489,
+      "learning_rate": 0.0002,
+      "loss": 0.9597,
+      "step": 1060
+    },
+    {
+      "epoch": 1.1713191023535852,
+      "grad_norm": 0.3650563359260559,
+      "learning_rate": 0.0002,
+      "loss": 1.0204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.3191976249217987,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1080
+    },
+    {
+      "epoch": 1.1932129173508483,
+      "grad_norm": 0.3615441918373108,
+      "learning_rate": 0.0002,
+      "loss": 1.0648,
+      "step": 1090
+    },
+    {
+      "epoch": 1.20415982484948,
+      "grad_norm": 0.39474231004714966,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2151067323481117,
+      "grad_norm": 0.3752822279930115,
+      "learning_rate": 0.0002,
+      "loss": 0.9852,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2260536398467432,
+      "grad_norm": 0.4165991246700287,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1120
+    },
+    {
+      "epoch": 1.237000547345375,
+      "grad_norm": 0.5326506495475769,
+      "learning_rate": 0.0002,
+      "loss": 1.0244,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2479474548440066,
+      "grad_norm": 0.48845794796943665,
+      "learning_rate": 0.0002,
+      "loss": 1.0542,
+      "step": 1140
+    },
+    {
+      "epoch": 1.2588943623426383,
+      "grad_norm": 0.29910150170326233,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.5069725513458252,
+      "learning_rate": 0.0002,
+      "loss": 1.2233,
+      "step": 1160
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 0.29500406980514526,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 1170
+    },
+    {
+      "epoch": 1.2917350848385332,
+      "grad_norm": 0.4711538851261139,
+      "learning_rate": 0.0002,
+      "loss": 1.0291,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3026819923371646,
+      "grad_norm": 0.4203340709209442,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1190
+    },
+    {
+      "epoch": 1.3136288998357963,
+      "grad_norm": 0.36101874709129333,
+      "learning_rate": 0.0002,
+      "loss": 1.1274,
+      "step": 1200
+    },
+    {
+      "epoch": 1.324575807334428,
+      "grad_norm": 0.4608800411224365,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 1210
+    },
+    {
+      "epoch": 1.3355227148330597,
+      "grad_norm": 0.6570906639099121,
+      "learning_rate": 0.0002,
+      "loss": 1.0695,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3464696223316914,
+      "grad_norm": 0.5352164506912231,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 1230
+    },
+    {
+      "epoch": 1.357416529830323,
+      "grad_norm": 0.3885001242160797,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1240
+    },
+    {
+      "epoch": 1.3683634373289546,
+      "grad_norm": 0.2987913489341736,
+      "learning_rate": 0.0002,
+      "loss": 1.0611,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.42070427536964417,
+      "learning_rate": 0.0002,
+      "loss": 1.109,
+      "step": 1260
+    },
+    {
+      "epoch": 1.3902572523262178,
+      "grad_norm": 0.5957782864570618,
+      "learning_rate": 0.0002,
+      "loss": 1.1092,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4012041598248495,
+      "grad_norm": 0.32898882031440735,
+      "learning_rate": 0.0002,
+      "loss": 1.0554,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4121510673234812,
+      "grad_norm": 0.27624452114105225,
+      "learning_rate": 0.0002,
+      "loss": 0.909,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4230979748221126,
+      "grad_norm": 0.49570828676223755,
+      "learning_rate": 0.0002,
+      "loss": 1.024,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4340448823207443,
+      "grad_norm": 0.26191383600234985,
+      "learning_rate": 0.0002,
+      "loss": 1.0471,
+      "step": 1310
+    },
+    {
+      "epoch": 1.444991789819376,
+      "grad_norm": 0.35664042830467224,
+      "learning_rate": 0.0002,
+      "loss": 1.0788,
+      "step": 1320
+    },
+    {
+      "epoch": 1.4559386973180077,
+      "grad_norm": 0.45126354694366455,
+      "learning_rate": 0.0002,
+      "loss": 1.0108,
+      "step": 1330
+    },
+    {
+      "epoch": 1.4668856048166394,
+      "grad_norm": 0.37318357825279236,
+      "learning_rate": 0.0002,
+      "loss": 0.9571,
+      "step": 1340
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 0.6428970098495483,
+      "learning_rate": 0.0002,
+      "loss": 1.0507,
+      "step": 1350
+    },
+    {
+      "epoch": 1.4887794198139026,
+      "grad_norm": 0.43256187438964844,
+      "learning_rate": 0.0002,
+      "loss": 1.0367,
+      "step": 1360
+    },
+    {
+      "epoch": 1.4997263273125343,
+      "grad_norm": 0.5343793630599976,
+      "learning_rate": 0.0002,
+      "loss": 1.1321,
+      "step": 1370
+    },
+    {
+      "epoch": 1.5106732348111658,
+      "grad_norm": 0.315437376499176,
+      "learning_rate": 0.0002,
+      "loss": 1.1054,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5216201423097975,
+      "grad_norm": 0.41561153531074524,
+      "learning_rate": 0.0002,
+      "loss": 0.8916,
+      "step": 1390
+    },
+    {
+      "epoch": 1.5325670498084292,
+      "grad_norm": 0.3201070725917816,
+      "learning_rate": 0.0002,
+      "loss": 1.0391,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5435139573070606,
+      "grad_norm": 0.505537211894989,
+      "learning_rate": 0.0002,
+      "loss": 1.14,
+      "step": 1410
+    },
+    {
+      "epoch": 1.5544608648056923,
+      "grad_norm": 0.3747410178184509,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 1420
+    },
+    {
+      "epoch": 1.565407772304324,
+      "grad_norm": 0.49385908246040344,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 1430
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 0.49831628799438477,
+      "learning_rate": 0.0002,
+      "loss": 1.1182,
+      "step": 1440
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.372127890586853,
+      "learning_rate": 0.0002,
+      "loss": 1.0079,
+      "step": 1450
+    },
+    {
+      "epoch": 1.598248494800219,
+      "grad_norm": 0.40070840716362,
+      "learning_rate": 0.0002,
+      "loss": 0.9931,
+      "step": 1460
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.34907400608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6201423097974823,
+      "grad_norm": 0.4632418751716614,
+      "learning_rate": 0.0002,
+      "loss": 0.9743,
+      "step": 1480
+    },
+    {
+      "epoch": 1.6310892172961138,
+      "grad_norm": 0.40164515376091003,
+      "learning_rate": 0.0002,
+      "loss": 1.0103,
+      "step": 1490
+    },
+    {
+      "epoch": 1.6420361247947455,
+      "grad_norm": 0.3214994966983795,
+      "learning_rate": 0.0002,
+      "loss": 0.9523,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6529830322933772,
+      "grad_norm": 0.3727897107601166,
+      "learning_rate": 0.0002,
+      "loss": 1.0161,
+      "step": 1510
+    },
+    {
+      "epoch": 1.6639299397920086,
+      "grad_norm": 0.3817640542984009,
+      "learning_rate": 0.0002,
+      "loss": 1.0443,
+      "step": 1520
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.5592136979103088,
+      "learning_rate": 0.0002,
+      "loss": 1.0511,
+      "step": 1530
+    },
+    {
+      "epoch": 1.685823754789272,
+      "grad_norm": 0.44636598229408264,
+      "learning_rate": 0.0002,
+      "loss": 0.9682,
+      "step": 1540
+    },
+    {
+      "epoch": 1.6967706622879035,
+      "grad_norm": 0.40441709756851196,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7077175697865354,
+      "grad_norm": 0.3243522644042969,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1560
+    },
+    {
+      "epoch": 1.718664477285167,
+      "grad_norm": 0.34277570247650146,
+      "learning_rate": 0.0002,
+      "loss": 0.9482,
+      "step": 1570
+    },
+    {
+      "epoch": 1.7296113847837986,
+      "grad_norm": 0.3279995024204254,
+      "learning_rate": 0.0002,
+      "loss": 0.974,
+      "step": 1580
+    },
+    {
+      "epoch": 1.7405582922824303,
+      "grad_norm": 0.41968777775764465,
+      "learning_rate": 0.0002,
+      "loss": 0.9414,
+      "step": 1590
+    },
+    {
+      "epoch": 1.7515051997810618,
+      "grad_norm": 0.39464613795280457,
+      "learning_rate": 0.0002,
+      "loss": 0.9768,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7624521072796935,
+      "grad_norm": 0.3839009404182434,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 1610
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 0.3250715434551239,
+      "learning_rate": 0.0002,
+      "loss": 0.9195,
+      "step": 1620
+    },
+    {
+      "epoch": 1.7843459222769567,
+      "grad_norm": 0.5166561007499695,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 1630
+    },
+    {
+      "epoch": 1.7952928297755884,
+      "grad_norm": 0.4115183353424072,
+      "learning_rate": 0.0002,
+      "loss": 1.0364,
+      "step": 1640
+    },
+    {
+      "epoch": 1.80623973727422,
+      "grad_norm": 0.373780220746994,
+      "learning_rate": 0.0002,
+      "loss": 1.0248,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8171866447728515,
+      "grad_norm": 0.49697014689445496,
+      "learning_rate": 0.0002,
+      "loss": 1.0984,
+      "step": 1660
+    },
+    {
+      "epoch": 1.8281335522714834,
+      "grad_norm": 1.0308938026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.0089,
+      "step": 1670
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.4851366877555847,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 1680
+    },
+    {
+      "epoch": 1.8500273672687466,
+      "grad_norm": 0.3262481391429901,
+      "learning_rate": 0.0002,
+      "loss": 0.9533,
+      "step": 1690
+    },
+    {
+      "epoch": 1.8609742747673783,
+      "grad_norm": 0.6904496550559998,
+      "learning_rate": 0.0002,
+      "loss": 1.048,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 0.49789851903915405,
+      "learning_rate": 0.0002,
+      "loss": 1.0577,
+      "step": 1710
+    },
+    {
+      "epoch": 1.8828680897646415,
+      "grad_norm": 0.3035794198513031,
+      "learning_rate": 0.0002,
+      "loss": 1.0258,
+      "step": 1720
+    },
+    {
+      "epoch": 1.8938149972632732,
+      "grad_norm": 0.4588414430618286,
+      "learning_rate": 0.0002,
+      "loss": 0.9916,
+      "step": 1730
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.4313034117221832,
+      "learning_rate": 0.0002,
+      "loss": 0.9526,
+      "step": 1740
+    },
+    {
+      "epoch": 1.9157088122605364,
+      "grad_norm": 0.38562044501304626,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1750
+    },
+    {
+      "epoch": 1.926655719759168,
+      "grad_norm": 0.46947410702705383,
+      "learning_rate": 0.0002,
+      "loss": 0.9763,
+      "step": 1760
+    },
+    {
+      "epoch": 1.9376026272577995,
+      "grad_norm": 0.3848404884338379,
+      "learning_rate": 0.0002,
+      "loss": 0.9967,
+      "step": 1770
+    },
+    {
+      "epoch": 1.9485495347564314,
+      "grad_norm": 0.30422744154930115,
+      "learning_rate": 0.0002,
+      "loss": 1.0474,
+      "step": 1780
+    },
+    {
+      "epoch": 1.959496442255063,
+      "grad_norm": 0.41100990772247314,
+      "learning_rate": 0.0002,
+      "loss": 1.022,
+      "step": 1790
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 0.3492335081100464,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9813902572523263,
+      "grad_norm": 0.364577978849411,
+      "learning_rate": 0.0002,
+      "loss": 0.9891,
+      "step": 1810
+    },
+    {
+      "epoch": 1.9923371647509578,
+      "grad_norm": 0.4312075674533844,
+      "learning_rate": 0.0002,
+      "loss": 1.0699,
+      "step": 1820
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.14472496509552,
+      "eval_runtime": 46.0786,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 1827
+    },
+    {
+      "epoch": 2.0032840722495897,
+      "grad_norm": 0.5989689230918884,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 1830
+    },
+    {
+      "epoch": 2.014230979748221,
+      "grad_norm": 0.49720922112464905,
+      "learning_rate": 0.0002,
+      "loss": 0.9384,
+      "step": 1840
+    },
+    {
+      "epoch": 2.0251778872468527,
+      "grad_norm": 0.42675456404685974,
+      "learning_rate": 0.0002,
+      "loss": 0.8482,
+      "step": 1850
+    },
+    {
+      "epoch": 2.0361247947454846,
+      "grad_norm": 0.4637208580970764,
+      "learning_rate": 0.0002,
+      "loss": 0.8487,
+      "step": 1860
+    },
+    {
+      "epoch": 2.047071702244116,
+      "grad_norm": 0.8329976797103882,
+      "learning_rate": 0.0002,
+      "loss": 0.8212,
+      "step": 1870
+    },
+    {
+      "epoch": 2.0580186097427475,
+      "grad_norm": 0.7869427800178528,
+      "learning_rate": 0.0002,
+      "loss": 0.9547,
+      "step": 1880
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.4927455186843872,
+      "learning_rate": 0.0002,
+      "loss": 0.9351,
+      "step": 1890
+    },
+    {
+      "epoch": 2.079912424740011,
+      "grad_norm": 0.6264246702194214,
+      "learning_rate": 0.0002,
+      "loss": 0.8652,
+      "step": 1900
+    },
+    {
+      "epoch": 2.0908593322386424,
+      "grad_norm": 1.1164122819900513,
+      "learning_rate": 0.0002,
+      "loss": 0.9095,
+      "step": 1910
+    },
+    {
+      "epoch": 2.1018062397372743,
+      "grad_norm": 0.5283981561660767,
+      "learning_rate": 0.0002,
+      "loss": 0.7823,
+      "step": 1920
+    },
+    {
+      "epoch": 2.112753147235906,
+      "grad_norm": 0.45621731877326965,
+      "learning_rate": 0.0002,
+      "loss": 0.8065,
+      "step": 1930
+    },
+    {
+      "epoch": 2.1237000547345373,
+      "grad_norm": 1.381791591644287,
+      "learning_rate": 0.0002,
+      "loss": 0.9184,
+      "step": 1940
+    },
+    {
+      "epoch": 2.134646962233169,
+      "grad_norm": 0.5151259899139404,
+      "learning_rate": 0.0002,
+      "loss": 0.9006,
+      "step": 1950
+    },
+    {
+      "epoch": 2.1455938697318007,
+      "grad_norm": 0.9806339740753174,
+      "learning_rate": 0.0002,
+      "loss": 0.8436,
+      "step": 1960
+    },
+    {
+      "epoch": 2.1565407772304326,
+      "grad_norm": 0.4734154939651489,
+      "learning_rate": 0.0002,
+      "loss": 0.8749,
+      "step": 1970
+    },
+    {
+      "epoch": 2.167487684729064,
+      "grad_norm": 0.9553168416023254,
+      "learning_rate": 0.0002,
+      "loss": 0.9172,
+      "step": 1980
+    },
+    {
+      "epoch": 2.1784345922276955,
+      "grad_norm": 0.5895838141441345,
+      "learning_rate": 0.0002,
+      "loss": 0.8047,
+      "step": 1990
+    },
+    {
+      "epoch": 2.1893814997263275,
+      "grad_norm": 0.4488855302333832,
+      "learning_rate": 0.0002,
+      "loss": 0.7841,
+      "step": 2000
+    },
+    {
+      "epoch": 2.200328407224959,
+      "grad_norm": 1.0760235786437988,
+      "learning_rate": 0.0002,
+      "loss": 0.8205,
+      "step": 2010
+    },
+    {
+      "epoch": 2.2112753147235904,
+      "grad_norm": 0.5038785338401794,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 2020
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.59819495677948,
+      "learning_rate": 0.0002,
+      "loss": 0.8973,
+      "step": 2030
+    },
+    {
+      "epoch": 2.233169129720854,
+      "grad_norm": 0.5012075304985046,
+      "learning_rate": 0.0002,
+      "loss": 0.8009,
+      "step": 2040
+    },
+    {
+      "epoch": 2.2441160372194853,
+      "grad_norm": 0.44978439807891846,
+      "learning_rate": 0.0002,
+      "loss": 0.9087,
+      "step": 2050
+    },
+    {
+      "epoch": 2.255062944718117,
+      "grad_norm": 0.5350462198257446,
+      "learning_rate": 0.0002,
+      "loss": 0.823,
+      "step": 2060
+    },
+    {
+      "epoch": 2.2660098522167487,
+      "grad_norm": 0.6020669937133789,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 2070
+    },
+    {
+      "epoch": 2.2769567597153806,
+      "grad_norm": 0.5246821045875549,
+      "learning_rate": 0.0002,
+      "loss": 0.8023,
+      "step": 2080
+    },
+    {
+      "epoch": 2.287903667214012,
+      "grad_norm": 0.5711268782615662,
+      "learning_rate": 0.0002,
+      "loss": 0.8984,
+      "step": 2090
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.617317259311676,
+      "learning_rate": 0.0002,
+      "loss": 0.9093,
+      "step": 2100
+    },
+    {
+      "epoch": 2.3097974822112755,
+      "grad_norm": 0.8608947396278381,
+      "learning_rate": 0.0002,
+      "loss": 0.8311,
+      "step": 2110
+    },
+    {
+      "epoch": 2.320744389709907,
+      "grad_norm": 0.4739076793193817,
+      "learning_rate": 0.0002,
+      "loss": 0.7839,
+      "step": 2120
+    },
+    {
+      "epoch": 2.3316912972085384,
+      "grad_norm": 0.5538856983184814,
+      "learning_rate": 0.0002,
+      "loss": 0.84,
+      "step": 2130
+    },
+    {
+      "epoch": 2.3426382047071703,
+      "grad_norm": 0.6064935326576233,
+      "learning_rate": 0.0002,
+      "loss": 0.8994,
+      "step": 2140
+    },
+    {
+      "epoch": 2.353585112205802,
+      "grad_norm": 0.5019068121910095,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 2150
+    },
+    {
+      "epoch": 2.3645320197044333,
+      "grad_norm": 0.45340514183044434,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 2160
+    },
+    {
+      "epoch": 2.375478927203065,
+      "grad_norm": 0.7347203493118286,
+      "learning_rate": 0.0002,
+      "loss": 0.9254,
+      "step": 2170
+    },
+    {
+      "epoch": 2.3864258347016967,
+      "grad_norm": 0.46922534704208374,
+      "learning_rate": 0.0002,
+      "loss": 0.8507,
+      "step": 2180
+    },
+    {
+      "epoch": 2.3973727422003286,
+      "grad_norm": 0.5507845878601074,
+      "learning_rate": 0.0002,
+      "loss": 0.8325,
+      "step": 2190
+    },
+    {
+      "epoch": 2.40831964969896,
+      "grad_norm": 0.5621911883354187,
+      "learning_rate": 0.0002,
+      "loss": 0.8178,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4192665571975915,
+      "grad_norm": 0.5023514032363892,
+      "learning_rate": 0.0002,
+      "loss": 0.8569,
+      "step": 2210
+    },
+    {
+      "epoch": 2.4302134646962235,
+      "grad_norm": 0.6124861240386963,
+      "learning_rate": 0.0002,
+      "loss": 0.8355,
+      "step": 2220
+    },
+    {
+      "epoch": 2.441160372194855,
+      "grad_norm": 0.49614205956459045,
+      "learning_rate": 0.0002,
+      "loss": 0.885,
+      "step": 2230
+    },
+    {
+      "epoch": 2.4521072796934864,
+      "grad_norm": 0.6477900743484497,
+      "learning_rate": 0.0002,
+      "loss": 0.8008,
+      "step": 2240
+    },
+    {
+      "epoch": 2.4630541871921183,
+      "grad_norm": 0.5868843793869019,
+      "learning_rate": 0.0002,
+      "loss": 0.8622,
+      "step": 2250
+    },
+    {
+      "epoch": 2.47400109469075,
+      "grad_norm": 0.4364610016345978,
+      "learning_rate": 0.0002,
+      "loss": 0.8498,
+      "step": 2260
+    },
+    {
+      "epoch": 2.4849480021893813,
+      "grad_norm": 0.5792964696884155,
+      "learning_rate": 0.0002,
+      "loss": 0.8378,
+      "step": 2270
+    },
+    {
+      "epoch": 2.495894909688013,
+      "grad_norm": 0.5421269536018372,
+      "learning_rate": 0.0002,
+      "loss": 0.8743,
+      "step": 2280
+    },
+    {
+      "epoch": 2.5068418171866447,
+      "grad_norm": 0.5525493025779724,
+      "learning_rate": 0.0002,
+      "loss": 0.9637,
+      "step": 2290
+    },
+    {
+      "epoch": 2.5177887246852766,
+      "grad_norm": 0.6463850140571594,
+      "learning_rate": 0.0002,
+      "loss": 0.8075,
+      "step": 2300
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.6861311793327332,
+      "learning_rate": 0.0002,
+      "loss": 0.8591,
+      "step": 2310
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.5563555359840393,
+      "learning_rate": 0.0002,
+      "loss": 0.9287,
+      "step": 2320
+    },
+    {
+      "epoch": 2.5506294471811715,
+      "grad_norm": 0.5721169114112854,
+      "learning_rate": 0.0002,
+      "loss": 0.945,
+      "step": 2330
+    },
+    {
+      "epoch": 2.561576354679803,
+      "grad_norm": 0.5258274674415588,
+      "learning_rate": 0.0002,
+      "loss": 0.8271,
+      "step": 2340
+    },
+    {
+      "epoch": 2.572523262178435,
+      "grad_norm": 0.7057380676269531,
+      "learning_rate": 0.0002,
+      "loss": 0.8515,
+      "step": 2350
+    },
+    {
+      "epoch": 2.5834701696770663,
+      "grad_norm": 0.6869027614593506,
+      "learning_rate": 0.0002,
+      "loss": 0.8615,
+      "step": 2360
+    },
+    {
+      "epoch": 2.594417077175698,
+      "grad_norm": 0.4960809648036957,
+      "learning_rate": 0.0002,
+      "loss": 0.8043,
+      "step": 2370
+    },
+    {
+      "epoch": 2.6053639846743293,
+      "grad_norm": 0.9288380146026611,
+      "learning_rate": 0.0002,
+      "loss": 0.8476,
+      "step": 2380
+    },
+    {
+      "epoch": 2.616310892172961,
+      "grad_norm": 0.3765334188938141,
+      "learning_rate": 0.0002,
+      "loss": 0.873,
+      "step": 2390
+    },
+    {
+      "epoch": 2.6272577996715927,
+      "grad_norm": 0.7487865686416626,
+      "learning_rate": 0.0002,
+      "loss": 0.8764,
+      "step": 2400
+    },
+    {
+      "epoch": 2.6382047071702246,
+      "grad_norm": 0.6141156554222107,
+      "learning_rate": 0.0002,
+      "loss": 0.7577,
+      "step": 2410
+    },
+    {
+      "epoch": 2.649151614668856,
+      "grad_norm": 0.8420507907867432,
+      "learning_rate": 0.0002,
+      "loss": 0.8534,
+      "step": 2420
+    },
+    {
+      "epoch": 2.6600985221674875,
+      "grad_norm": 0.53386390209198,
+      "learning_rate": 0.0002,
+      "loss": 0.8311,
+      "step": 2430
+    },
+    {
+      "epoch": 2.6710454296661195,
+      "grad_norm": 0.5520607233047485,
+      "learning_rate": 0.0002,
+      "loss": 0.8486,
+      "step": 2440
+    },
+    {
+      "epoch": 2.681992337164751,
+      "grad_norm": 0.5337599515914917,
+      "learning_rate": 0.0002,
+      "loss": 0.8686,
+      "step": 2450
+    },
+    {
+      "epoch": 2.692939244663383,
+      "grad_norm": 0.48790836334228516,
+      "learning_rate": 0.0002,
+      "loss": 0.792,
+      "step": 2460
+    },
+    {
+      "epoch": 2.7038861521620143,
+      "grad_norm": 0.8287786245346069,
+      "learning_rate": 0.0002,
+      "loss": 0.7864,
+      "step": 2470
+    },
+    {
+      "epoch": 2.714833059660646,
+      "grad_norm": 0.5876168608665466,
+      "learning_rate": 0.0002,
+      "loss": 0.8244,
+      "step": 2480
+    },
+    {
+      "epoch": 2.7257799671592773,
+      "grad_norm": 0.5206760764122009,
+      "learning_rate": 0.0002,
+      "loss": 0.8773,
+      "step": 2490
+    },
+    {
+      "epoch": 2.736726874657909,
+      "grad_norm": 0.5619136691093445,
+      "learning_rate": 0.0002,
+      "loss": 0.8097,
+      "step": 2500
+    },
+    {
+      "epoch": 2.7476737821565407,
+      "grad_norm": 0.5614883899688721,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 2510
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.6157700419425964,
+      "learning_rate": 0.0002,
+      "loss": 0.8817,
+      "step": 2520
+    },
+    {
+      "epoch": 2.769567597153804,
+      "grad_norm": 0.5529953837394714,
+      "learning_rate": 0.0002,
+      "loss": 0.846,
+      "step": 2530
+    },
+    {
+      "epoch": 2.7805145046524355,
+      "grad_norm": 0.6731224060058594,
+      "learning_rate": 0.0002,
+      "loss": 0.8881,
+      "step": 2540
+    },
+    {
+      "epoch": 2.7914614121510675,
+      "grad_norm": 0.6960386633872986,
+      "learning_rate": 0.0002,
+      "loss": 0.9125,
+      "step": 2550
+    },
+    {
+      "epoch": 2.802408319649699,
+      "grad_norm": 0.5203493237495422,
+      "learning_rate": 0.0002,
+      "loss": 0.7823,
+      "step": 2560
+    },
+    {
+      "epoch": 2.813355227148331,
+      "grad_norm": 1.036837100982666,
+      "learning_rate": 0.0002,
+      "loss": 0.7951,
+      "step": 2570
+    },
+    {
+      "epoch": 2.8243021346469623,
+      "grad_norm": 0.6125805377960205,
+      "learning_rate": 0.0002,
+      "loss": 0.8427,
+      "step": 2580
+    },
+    {
+      "epoch": 2.835249042145594,
+      "grad_norm": 0.6298092603683472,
+      "learning_rate": 0.0002,
+      "loss": 0.8939,
+      "step": 2590
+    },
+    {
+      "epoch": 2.8461959496442253,
+      "grad_norm": 0.5882203578948975,
+      "learning_rate": 0.0002,
+      "loss": 0.8845,
+      "step": 2600
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.8619399666786194,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 2610
+    },
+    {
+      "epoch": 2.8680897646414887,
+      "grad_norm": 0.4722687304019928,
+      "learning_rate": 0.0002,
+      "loss": 0.8213,
+      "step": 2620
+    },
+    {
+      "epoch": 2.8790366721401206,
+      "grad_norm": 0.47399574518203735,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 2630
+    },
+    {
+      "epoch": 2.889983579638752,
+      "grad_norm": 0.5639172792434692,
+      "learning_rate": 0.0002,
+      "loss": 0.8325,
+      "step": 2640
+    },
+    {
+      "epoch": 2.9009304871373836,
+      "grad_norm": 0.4676816761493683,
+      "learning_rate": 0.0002,
+      "loss": 0.8653,
+      "step": 2650
+    },
+    {
+      "epoch": 2.9118773946360155,
+      "grad_norm": 0.6906291246414185,
+      "learning_rate": 0.0002,
+      "loss": 0.8966,
+      "step": 2660
+    },
+    {
+      "epoch": 2.922824302134647,
+      "grad_norm": 0.4369746148586273,
+      "learning_rate": 0.0002,
+      "loss": 0.8966,
+      "step": 2670
+    },
+    {
+      "epoch": 2.933771209633279,
+      "grad_norm": 0.46423083543777466,
+      "learning_rate": 0.0002,
+      "loss": 0.9173,
+      "step": 2680
+    },
+    {
+      "epoch": 2.9447181171319103,
+      "grad_norm": 0.5700525045394897,
+      "learning_rate": 0.0002,
+      "loss": 0.7961,
+      "step": 2690
+    },
+    {
+      "epoch": 2.955665024630542,
+      "grad_norm": 0.6221476793289185,
+      "learning_rate": 0.0002,
+      "loss": 0.8172,
+      "step": 2700
+    },
+    {
+      "epoch": 2.9666119321291733,
+      "grad_norm": 0.6102682948112488,
+      "learning_rate": 0.0002,
+      "loss": 0.8538,
+      "step": 2710
+    },
+    {
+      "epoch": 2.977558839627805,
+      "grad_norm": 0.5317878723144531,
+      "learning_rate": 0.0002,
+      "loss": 0.9779,
+      "step": 2720
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.4438510835170746,
+      "learning_rate": 0.0002,
+      "loss": 0.9314,
+      "step": 2730
+    },
+    {
+      "epoch": 2.9994526546250686,
+      "grad_norm": 0.5022130012512207,
+      "learning_rate": 0.0002,
+      "loss": 0.8553,
+      "step": 2740
+    },
+    {
+      "epoch": 2.9994526546250686,
+      "eval_loss": 1.1722838878631592,
+      "eval_runtime": 46.0829,
+      "eval_samples_per_second": 9.461,
+      "eval_steps_per_second": 1.194,
+      "step": 2740
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7304,
+  "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": 1.4076234489397248e+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-4/checkpoint-2740/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a158bca77bc6d58bfffd2acd2e9e641d481e1857fcbdd68fee875b74797abbc4
+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-4/checkpoint-3654/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-4/checkpoint-3654/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-4/checkpoint-3654/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84388d4ac5738c377bd47af9ca50506439a278bc680479cf2db90b15345be18
+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-4/checkpoint-3654/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93866aa1024d72e1ac54b17d93e37aa192ee0d448c3afaeafe3afb9d48dbf0de
+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-4/checkpoint-3654/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06f9b81fb40fc97b17f99738dd19e250800243191cab070d3f261467f044a84
+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-4/checkpoint-3654/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5002c510756345ccba22822baa17f31534958c278f8a15afb59f45002a8e21d9
+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-4/checkpoint-3654/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-4/checkpoint-3654/tokenizer.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/checkpoint-3654/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-4/checkpoint-3654/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-4/checkpoint-3654/trainer_state.json

@@ -0,0 +1,2620 @@
+{
+  "best_metric": 1.14472496509552,
+  "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-4/checkpoint-1827",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 3654,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010946907498631636,
+      "grad_norm": 0.7611560821533203,
+      "learning_rate": 0.0002,
+      "loss": 2.4039,
+      "step": 10
+    },
+    {
+      "epoch": 0.021893814997263273,
+      "grad_norm": 0.4633193612098694,
+      "learning_rate": 0.0002,
+      "loss": 1.8818,
+      "step": 20
+    },
+    {
+      "epoch": 0.03284072249589491,
+      "grad_norm": 0.49326154589653015,
+      "learning_rate": 0.0002,
+      "loss": 1.5927,
+      "step": 30
+    },
+    {
+      "epoch": 0.043787629994526546,
+      "grad_norm": 0.3943138122558594,
+      "learning_rate": 0.0002,
+      "loss": 1.3859,
+      "step": 40
+    },
+    {
+      "epoch": 0.05473453749315818,
+      "grad_norm": 0.43292930722236633,
+      "learning_rate": 0.0002,
+      "loss": 1.3036,
+      "step": 50
+    },
+    {
+      "epoch": 0.06568144499178982,
+      "grad_norm": 0.3431817591190338,
+      "learning_rate": 0.0002,
+      "loss": 1.2427,
+      "step": 60
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.38011446595191956,
+      "learning_rate": 0.0002,
+      "loss": 1.3076,
+      "step": 70
+    },
+    {
+      "epoch": 0.08757525998905309,
+      "grad_norm": 0.7441071271896362,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 80
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.3359833061695099,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 90
+    },
+    {
+      "epoch": 0.10946907498631636,
+      "grad_norm": 0.3724392354488373,
+      "learning_rate": 0.0002,
+      "loss": 1.2774,
+      "step": 100
+    },
+    {
+      "epoch": 0.120415982484948,
+      "grad_norm": 0.40673762559890747,
+      "learning_rate": 0.0002,
+      "loss": 1.216,
+      "step": 110
+    },
+    {
+      "epoch": 0.13136288998357964,
+      "grad_norm": 0.40036800503730774,
+      "learning_rate": 0.0002,
+      "loss": 1.2611,
+      "step": 120
+    },
+    {
+      "epoch": 0.1423097974822113,
+      "grad_norm": 2.844191312789917,
+      "learning_rate": 0.0002,
+      "loss": 1.2436,
+      "step": 130
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.3104734420776367,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "step": 140
+    },
+    {
+      "epoch": 0.16420361247947454,
+      "grad_norm": 0.3266797959804535,
+      "learning_rate": 0.0002,
+      "loss": 1.0498,
+      "step": 150
+    },
+    {
+      "epoch": 0.17515051997810618,
+      "grad_norm": 0.3079199194908142,
+      "learning_rate": 0.0002,
+      "loss": 1.1644,
+      "step": 160
+    },
+    {
+      "epoch": 0.18609742747673783,
+      "grad_norm": 0.3872479498386383,
+      "learning_rate": 0.0002,
+      "loss": 1.2923,
+      "step": 170
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.38654500246047974,
+      "learning_rate": 0.0002,
+      "loss": 1.1809,
+      "step": 180
+    },
+    {
+      "epoch": 0.20799124247400108,
+      "grad_norm": 0.2913552522659302,
+      "learning_rate": 0.0002,
+      "loss": 1.066,
+      "step": 190
+    },
+    {
+      "epoch": 0.21893814997263272,
+      "grad_norm": 0.2960572838783264,
+      "learning_rate": 0.0002,
+      "loss": 1.0868,
+      "step": 200
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.5175501108169556,
+      "learning_rate": 0.0002,
+      "loss": 1.136,
+      "step": 210
+    },
+    {
+      "epoch": 0.240831964969896,
+      "grad_norm": 1.2921574115753174,
+      "learning_rate": 0.0002,
+      "loss": 1.1556,
+      "step": 220
+    },
+    {
+      "epoch": 0.25177887246852765,
+      "grad_norm": 0.2675512135028839,
+      "learning_rate": 0.0002,
+      "loss": 1.1488,
+      "step": 230
+    },
+    {
+      "epoch": 0.2627257799671593,
+      "grad_norm": 0.3956190049648285,
+      "learning_rate": 0.0002,
+      "loss": 1.2764,
+      "step": 240
+    },
+    {
+      "epoch": 0.27367268746579093,
+      "grad_norm": 0.6022581458091736,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 250
+    },
+    {
+      "epoch": 0.2846195949644226,
+      "grad_norm": 1.1949563026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.1981,
+      "step": 260
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.31173548102378845,
+      "learning_rate": 0.0002,
+      "loss": 1.1877,
+      "step": 270
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2808472812175751,
+      "learning_rate": 0.0002,
+      "loss": 1.06,
+      "step": 280
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.3042023777961731,
+      "learning_rate": 0.0002,
+      "loss": 1.1752,
+      "step": 290
+    },
+    {
+      "epoch": 0.3284072249589491,
+      "grad_norm": 0.39915043115615845,
+      "learning_rate": 0.0002,
+      "loss": 1.3147,
+      "step": 300
+    },
+    {
+      "epoch": 0.3393541324575807,
+      "grad_norm": 0.39118197560310364,
+      "learning_rate": 0.0002,
+      "loss": 1.2425,
+      "step": 310
+    },
+    {
+      "epoch": 0.35030103995621237,
+      "grad_norm": 0.355010986328125,
+      "learning_rate": 0.0002,
+      "loss": 1.1363,
+      "step": 320
+    },
+    {
+      "epoch": 0.361247947454844,
+      "grad_norm": 0.29734086990356445,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 330
+    },
+    {
+      "epoch": 0.37219485495347565,
+      "grad_norm": 0.346096009016037,
+      "learning_rate": 0.0002,
+      "loss": 1.1974,
+      "step": 340
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.4829643666744232,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 350
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.4726872742176056,
+      "learning_rate": 0.0002,
+      "loss": 1.2808,
+      "step": 360
+    },
+    {
+      "epoch": 0.4050355774493706,
+      "grad_norm": 0.3130153715610504,
+      "learning_rate": 0.0002,
+      "loss": 1.1532,
+      "step": 370
+    },
+    {
+      "epoch": 0.41598248494800216,
+      "grad_norm": 0.5123590230941772,
+      "learning_rate": 0.0002,
+      "loss": 1.1842,
+      "step": 380
+    },
+    {
+      "epoch": 0.4269293924466338,
+      "grad_norm": 0.3444574773311615,
+      "learning_rate": 0.0002,
+      "loss": 1.1539,
+      "step": 390
+    },
+    {
+      "epoch": 0.43787629994526545,
+      "grad_norm": 0.5302175283432007,
+      "learning_rate": 0.0002,
+      "loss": 1.1756,
+      "step": 400
+    },
+    {
+      "epoch": 0.4488232074438971,
+      "grad_norm": 0.2713572680950165,
+      "learning_rate": 0.0002,
+      "loss": 1.1138,
+      "step": 410
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.29530611634254456,
+      "learning_rate": 0.0002,
+      "loss": 1.1281,
+      "step": 420
+    },
+    {
+      "epoch": 0.47071702244116037,
+      "grad_norm": 0.27282455563545227,
+      "learning_rate": 0.0002,
+      "loss": 1.1721,
+      "step": 430
+    },
+    {
+      "epoch": 0.481663929939792,
+      "grad_norm": 0.2647949755191803,
+      "learning_rate": 0.0002,
+      "loss": 1.1213,
+      "step": 440
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.35509347915649414,
+      "learning_rate": 0.0002,
+      "loss": 1.1656,
+      "step": 450
+    },
+    {
+      "epoch": 0.5035577449370553,
+      "grad_norm": 0.1959609091281891,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 460
+    },
+    {
+      "epoch": 0.5145046524356869,
+      "grad_norm": 0.40090155601501465,
+      "learning_rate": 0.0002,
+      "loss": 1.1889,
+      "step": 470
+    },
+    {
+      "epoch": 0.5254515599343186,
+      "grad_norm": 0.3354604244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.156,
+      "step": 480
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.2758506238460541,
+      "learning_rate": 0.0002,
+      "loss": 1.1024,
+      "step": 490
+    },
+    {
+      "epoch": 0.5473453749315819,
+      "grad_norm": 0.3629051744937897,
+      "learning_rate": 0.0002,
+      "loss": 1.1108,
+      "step": 500
+    },
+    {
+      "epoch": 0.5582922824302134,
+      "grad_norm": 0.30802229046821594,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 510
+    },
+    {
+      "epoch": 0.5692391899288451,
+      "grad_norm": 0.3099463880062103,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 520
+    },
+    {
+      "epoch": 0.5801860974274767,
+      "grad_norm": 0.42299067974090576,
+      "learning_rate": 0.0002,
+      "loss": 1.255,
+      "step": 530
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.5392252802848816,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 0.60207991242474,
+      "grad_norm": 0.34768250584602356,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 550
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.28490015864372253,
+      "learning_rate": 0.0002,
+      "loss": 1.102,
+      "step": 560
+    },
+    {
+      "epoch": 0.6239737274220033,
+      "grad_norm": 0.34787994623184204,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 570
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.29058772325515747,
+      "learning_rate": 0.0002,
+      "loss": 1.0759,
+      "step": 580
+    },
+    {
+      "epoch": 0.6458675424192666,
+      "grad_norm": 0.4063778817653656,
+      "learning_rate": 0.0002,
+      "loss": 1.1157,
+      "step": 590
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.9244267344474792,
+      "learning_rate": 0.0002,
+      "loss": 1.1432,
+      "step": 600
+    },
+    {
+      "epoch": 0.6677613574165299,
+      "grad_norm": 0.27605190873146057,
+      "learning_rate": 0.0002,
+      "loss": 1.0591,
+      "step": 610
+    },
+    {
+      "epoch": 0.6787082649151615,
+      "grad_norm": 0.34346821904182434,
+      "learning_rate": 0.0002,
+      "loss": 1.2123,
+      "step": 620
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.3093279302120209,
+      "learning_rate": 0.0002,
+      "loss": 1.2195,
+      "step": 630
+    },
+    {
+      "epoch": 0.7006020799124247,
+      "grad_norm": 1.0069009065628052,
+      "learning_rate": 0.0002,
+      "loss": 1.2461,
+      "step": 640
+    },
+    {
+      "epoch": 0.7115489874110563,
+      "grad_norm": 0.5049130916595459,
+      "learning_rate": 0.0002,
+      "loss": 1.0892,
+      "step": 650
+    },
+    {
+      "epoch": 0.722495894909688,
+      "grad_norm": 0.3748924732208252,
+      "learning_rate": 0.0002,
+      "loss": 1.1404,
+      "step": 660
+    },
+    {
+      "epoch": 0.7334428024083196,
+      "grad_norm": 0.2964959144592285,
+      "learning_rate": 0.0002,
+      "loss": 1.1062,
+      "step": 670
+    },
+    {
+      "epoch": 0.7443897099069513,
+      "grad_norm": 0.4599986970424652,
+      "learning_rate": 0.0002,
+      "loss": 1.2617,
+      "step": 680
+    },
+    {
+      "epoch": 0.7553366174055829,
+      "grad_norm": 0.27292951941490173,
+      "learning_rate": 0.0002,
+      "loss": 1.088,
+      "step": 690
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.3123566806316376,
+      "learning_rate": 0.0002,
+      "loss": 1.2047,
+      "step": 700
+    },
+    {
+      "epoch": 0.7772304324028462,
+      "grad_norm": 0.28310710191726685,
+      "learning_rate": 0.0002,
+      "loss": 1.0021,
+      "step": 710
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.3279992341995239,
+      "learning_rate": 0.0002,
+      "loss": 1.2281,
+      "step": 720
+    },
+    {
+      "epoch": 0.7991242474001095,
+      "grad_norm": 0.28179168701171875,
+      "learning_rate": 0.0002,
+      "loss": 1.25,
+      "step": 730
+    },
+    {
+      "epoch": 0.8100711548987412,
+      "grad_norm": 0.31492987275123596,
+      "learning_rate": 0.0002,
+      "loss": 1.0602,
+      "step": 740
+    },
+    {
+      "epoch": 0.8210180623973727,
+      "grad_norm": 0.41821011900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.2518,
+      "step": 750
+    },
+    {
+      "epoch": 0.8319649698960043,
+      "grad_norm": 0.325235515832901,
+      "learning_rate": 0.0002,
+      "loss": 1.1612,
+      "step": 760
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.5366070866584778,
+      "learning_rate": 0.0002,
+      "loss": 1.27,
+      "step": 770
+    },
+    {
+      "epoch": 0.8538587848932676,
+      "grad_norm": 0.32570579648017883,
+      "learning_rate": 0.0002,
+      "loss": 1.0921,
+      "step": 780
+    },
+    {
+      "epoch": 0.8648056923918993,
+      "grad_norm": 0.3642968237400055,
+      "learning_rate": 0.0002,
+      "loss": 1.1032,
+      "step": 790
+    },
+    {
+      "epoch": 0.8757525998905309,
+      "grad_norm": 0.29713448882102966,
+      "learning_rate": 0.0002,
+      "loss": 1.1234,
+      "step": 800
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.23599444329738617,
+      "learning_rate": 0.0002,
+      "loss": 1.0978,
+      "step": 810
+    },
+    {
+      "epoch": 0.8976464148877942,
+      "grad_norm": 0.31522464752197266,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 820
+    },
+    {
+      "epoch": 0.9085933223864259,
+      "grad_norm": 0.32754790782928467,
+      "learning_rate": 0.0002,
+      "loss": 1.0208,
+      "step": 830
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22741089761257172,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 840
+    },
+    {
+      "epoch": 0.9304871373836892,
+      "grad_norm": 0.3089679777622223,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 850
+    },
+    {
+      "epoch": 0.9414340448823207,
+      "grad_norm": 0.27440521121025085,
+      "learning_rate": 0.0002,
+      "loss": 1.0354,
+      "step": 860
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3498363792896271,
+      "learning_rate": 0.0002,
+      "loss": 1.0417,
+      "step": 870
+    },
+    {
+      "epoch": 0.963327859879584,
+      "grad_norm": 0.47151854634284973,
+      "learning_rate": 0.0002,
+      "loss": 1.269,
+      "step": 880
+    },
+    {
+      "epoch": 0.9742747673782156,
+      "grad_norm": 0.24756591022014618,
+      "learning_rate": 0.0002,
+      "loss": 1.1174,
+      "step": 890
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.2600938677787781,
+      "learning_rate": 0.0002,
+      "loss": 1.0622,
+      "step": 900
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.2934586703777313,
+      "learning_rate": 0.0002,
+      "loss": 1.0968,
+      "step": 910
+    },
+    {
+      "epoch": 0.9994526546250684,
+      "eval_loss": 1.158464789390564,
+      "eval_runtime": 46.0774,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 913
+    },
+    {
+      "epoch": 1.0071154898741106,
+      "grad_norm": 0.37776654958724976,
+      "learning_rate": 0.0002,
+      "loss": 1.0322,
+      "step": 920
+    },
+    {
+      "epoch": 1.0180623973727423,
+      "grad_norm": 0.31784629821777344,
+      "learning_rate": 0.0002,
+      "loss": 1.1346,
+      "step": 930
+    },
+    {
+      "epoch": 1.0290093048713738,
+      "grad_norm": 0.24244336783885956,
+      "learning_rate": 0.0002,
+      "loss": 0.8976,
+      "step": 940
+    },
+    {
+      "epoch": 1.0399562123700055,
+      "grad_norm": 0.3185454308986664,
+      "learning_rate": 0.0002,
+      "loss": 1.0172,
+      "step": 950
+    },
+    {
+      "epoch": 1.0509031198686372,
+      "grad_norm": 0.3589441478252411,
+      "learning_rate": 0.0002,
+      "loss": 1.1645,
+      "step": 960
+    },
+    {
+      "epoch": 1.0618500273672686,
+      "grad_norm": 0.38593578338623047,
+      "learning_rate": 0.0002,
+      "loss": 1.0317,
+      "step": 970
+    },
+    {
+      "epoch": 1.0727969348659003,
+      "grad_norm": 0.39694955945014954,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 980
+    },
+    {
+      "epoch": 1.083743842364532,
+      "grad_norm": 0.469817191362381,
+      "learning_rate": 0.0002,
+      "loss": 1.0893,
+      "step": 990
+    },
+    {
+      "epoch": 1.0946907498631637,
+      "grad_norm": 0.2634755074977875,
+      "learning_rate": 0.0002,
+      "loss": 0.983,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1056376573617952,
+      "grad_norm": 0.43189436197280884,
+      "learning_rate": 0.0002,
+      "loss": 1.0144,
+      "step": 1010
+    },
+    {
+      "epoch": 1.116584564860427,
+      "grad_norm": 0.5559977889060974,
+      "learning_rate": 0.0002,
+      "loss": 0.9663,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1275314723590586,
+      "grad_norm": 0.32100191712379456,
+      "learning_rate": 0.0002,
+      "loss": 1.0481,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1384783798576903,
+      "grad_norm": 0.40179768204689026,
+      "learning_rate": 0.0002,
+      "loss": 1.1012,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.3659493029117584,
+      "learning_rate": 0.0002,
+      "loss": 1.0029,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1603721948549535,
+      "grad_norm": 0.701704204082489,
+      "learning_rate": 0.0002,
+      "loss": 0.9597,
+      "step": 1060
+    },
+    {
+      "epoch": 1.1713191023535852,
+      "grad_norm": 0.3650563359260559,
+      "learning_rate": 0.0002,
+      "loss": 1.0204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.3191976249217987,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1080
+    },
+    {
+      "epoch": 1.1932129173508483,
+      "grad_norm": 0.3615441918373108,
+      "learning_rate": 0.0002,
+      "loss": 1.0648,
+      "step": 1090
+    },
+    {
+      "epoch": 1.20415982484948,
+      "grad_norm": 0.39474231004714966,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2151067323481117,
+      "grad_norm": 0.3752822279930115,
+      "learning_rate": 0.0002,
+      "loss": 0.9852,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2260536398467432,
+      "grad_norm": 0.4165991246700287,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 1120
+    },
+    {
+      "epoch": 1.237000547345375,
+      "grad_norm": 0.5326506495475769,
+      "learning_rate": 0.0002,
+      "loss": 1.0244,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2479474548440066,
+      "grad_norm": 0.48845794796943665,
+      "learning_rate": 0.0002,
+      "loss": 1.0542,
+      "step": 1140
+    },
+    {
+      "epoch": 1.2588943623426383,
+      "grad_norm": 0.29910150170326233,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.5069725513458252,
+      "learning_rate": 0.0002,
+      "loss": 1.2233,
+      "step": 1160
+    },
+    {
+      "epoch": 1.2807881773399015,
+      "grad_norm": 0.29500406980514526,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 1170
+    },
+    {
+      "epoch": 1.2917350848385332,
+      "grad_norm": 0.4711538851261139,
+      "learning_rate": 0.0002,
+      "loss": 1.0291,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3026819923371646,
+      "grad_norm": 0.4203340709209442,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1190
+    },
+    {
+      "epoch": 1.3136288998357963,
+      "grad_norm": 0.36101874709129333,
+      "learning_rate": 0.0002,
+      "loss": 1.1274,
+      "step": 1200
+    },
+    {
+      "epoch": 1.324575807334428,
+      "grad_norm": 0.4608800411224365,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 1210
+    },
+    {
+      "epoch": 1.3355227148330597,
+      "grad_norm": 0.6570906639099121,
+      "learning_rate": 0.0002,
+      "loss": 1.0695,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3464696223316914,
+      "grad_norm": 0.5352164506912231,
+      "learning_rate": 0.0002,
+      "loss": 0.9786,
+      "step": 1230
+    },
+    {
+      "epoch": 1.357416529830323,
+      "grad_norm": 0.3885001242160797,
+      "learning_rate": 0.0002,
+      "loss": 1.0513,
+      "step": 1240
+    },
+    {
+      "epoch": 1.3683634373289546,
+      "grad_norm": 0.2987913489341736,
+      "learning_rate": 0.0002,
+      "loss": 1.0611,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.42070427536964417,
+      "learning_rate": 0.0002,
+      "loss": 1.109,
+      "step": 1260
+    },
+    {
+      "epoch": 1.3902572523262178,
+      "grad_norm": 0.5957782864570618,
+      "learning_rate": 0.0002,
+      "loss": 1.1092,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4012041598248495,
+      "grad_norm": 0.32898882031440735,
+      "learning_rate": 0.0002,
+      "loss": 1.0554,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4121510673234812,
+      "grad_norm": 0.27624452114105225,
+      "learning_rate": 0.0002,
+      "loss": 0.909,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4230979748221126,
+      "grad_norm": 0.49570828676223755,
+      "learning_rate": 0.0002,
+      "loss": 1.024,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4340448823207443,
+      "grad_norm": 0.26191383600234985,
+      "learning_rate": 0.0002,
+      "loss": 1.0471,
+      "step": 1310
+    },
+    {
+      "epoch": 1.444991789819376,
+      "grad_norm": 0.35664042830467224,
+      "learning_rate": 0.0002,
+      "loss": 1.0788,
+      "step": 1320
+    },
+    {
+      "epoch": 1.4559386973180077,
+      "grad_norm": 0.45126354694366455,
+      "learning_rate": 0.0002,
+      "loss": 1.0108,
+      "step": 1330
+    },
+    {
+      "epoch": 1.4668856048166394,
+      "grad_norm": 0.37318357825279236,
+      "learning_rate": 0.0002,
+      "loss": 0.9571,
+      "step": 1340
+    },
+    {
+      "epoch": 1.477832512315271,
+      "grad_norm": 0.6428970098495483,
+      "learning_rate": 0.0002,
+      "loss": 1.0507,
+      "step": 1350
+    },
+    {
+      "epoch": 1.4887794198139026,
+      "grad_norm": 0.43256187438964844,
+      "learning_rate": 0.0002,
+      "loss": 1.0367,
+      "step": 1360
+    },
+    {
+      "epoch": 1.4997263273125343,
+      "grad_norm": 0.5343793630599976,
+      "learning_rate": 0.0002,
+      "loss": 1.1321,
+      "step": 1370
+    },
+    {
+      "epoch": 1.5106732348111658,
+      "grad_norm": 0.315437376499176,
+      "learning_rate": 0.0002,
+      "loss": 1.1054,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5216201423097975,
+      "grad_norm": 0.41561153531074524,
+      "learning_rate": 0.0002,
+      "loss": 0.8916,
+      "step": 1390
+    },
+    {
+      "epoch": 1.5325670498084292,
+      "grad_norm": 0.3201070725917816,
+      "learning_rate": 0.0002,
+      "loss": 1.0391,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5435139573070606,
+      "grad_norm": 0.505537211894989,
+      "learning_rate": 0.0002,
+      "loss": 1.14,
+      "step": 1410
+    },
+    {
+      "epoch": 1.5544608648056923,
+      "grad_norm": 0.3747410178184509,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 1420
+    },
+    {
+      "epoch": 1.565407772304324,
+      "grad_norm": 0.49385908246040344,
+      "learning_rate": 0.0002,
+      "loss": 1.1171,
+      "step": 1430
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 0.49831628799438477,
+      "learning_rate": 0.0002,
+      "loss": 1.1182,
+      "step": 1440
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.372127890586853,
+      "learning_rate": 0.0002,
+      "loss": 1.0079,
+      "step": 1450
+    },
+    {
+      "epoch": 1.598248494800219,
+      "grad_norm": 0.40070840716362,
+      "learning_rate": 0.0002,
+      "loss": 0.9931,
+      "step": 1460
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.34907400608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6201423097974823,
+      "grad_norm": 0.4632418751716614,
+      "learning_rate": 0.0002,
+      "loss": 0.9743,
+      "step": 1480
+    },
+    {
+      "epoch": 1.6310892172961138,
+      "grad_norm": 0.40164515376091003,
+      "learning_rate": 0.0002,
+      "loss": 1.0103,
+      "step": 1490
+    },
+    {
+      "epoch": 1.6420361247947455,
+      "grad_norm": 0.3214994966983795,
+      "learning_rate": 0.0002,
+      "loss": 0.9523,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6529830322933772,
+      "grad_norm": 0.3727897107601166,
+      "learning_rate": 0.0002,
+      "loss": 1.0161,
+      "step": 1510
+    },
+    {
+      "epoch": 1.6639299397920086,
+      "grad_norm": 0.3817640542984009,
+      "learning_rate": 0.0002,
+      "loss": 1.0443,
+      "step": 1520
+    },
+    {
+      "epoch": 1.6748768472906403,
+      "grad_norm": 0.5592136979103088,
+      "learning_rate": 0.0002,
+      "loss": 1.0511,
+      "step": 1530
+    },
+    {
+      "epoch": 1.685823754789272,
+      "grad_norm": 0.44636598229408264,
+      "learning_rate": 0.0002,
+      "loss": 0.9682,
+      "step": 1540
+    },
+    {
+      "epoch": 1.6967706622879035,
+      "grad_norm": 0.40441709756851196,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7077175697865354,
+      "grad_norm": 0.3243522644042969,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1560
+    },
+    {
+      "epoch": 1.718664477285167,
+      "grad_norm": 0.34277570247650146,
+      "learning_rate": 0.0002,
+      "loss": 0.9482,
+      "step": 1570
+    },
+    {
+      "epoch": 1.7296113847837986,
+      "grad_norm": 0.3279995024204254,
+      "learning_rate": 0.0002,
+      "loss": 0.974,
+      "step": 1580
+    },
+    {
+      "epoch": 1.7405582922824303,
+      "grad_norm": 0.41968777775764465,
+      "learning_rate": 0.0002,
+      "loss": 0.9414,
+      "step": 1590
+    },
+    {
+      "epoch": 1.7515051997810618,
+      "grad_norm": 0.39464613795280457,
+      "learning_rate": 0.0002,
+      "loss": 0.9768,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7624521072796935,
+      "grad_norm": 0.3839009404182434,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 1610
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 0.3250715434551239,
+      "learning_rate": 0.0002,
+      "loss": 0.9195,
+      "step": 1620
+    },
+    {
+      "epoch": 1.7843459222769567,
+      "grad_norm": 0.5166561007499695,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 1630
+    },
+    {
+      "epoch": 1.7952928297755884,
+      "grad_norm": 0.4115183353424072,
+      "learning_rate": 0.0002,
+      "loss": 1.0364,
+      "step": 1640
+    },
+    {
+      "epoch": 1.80623973727422,
+      "grad_norm": 0.373780220746994,
+      "learning_rate": 0.0002,
+      "loss": 1.0248,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8171866447728515,
+      "grad_norm": 0.49697014689445496,
+      "learning_rate": 0.0002,
+      "loss": 1.0984,
+      "step": 1660
+    },
+    {
+      "epoch": 1.8281335522714834,
+      "grad_norm": 1.0308938026428223,
+      "learning_rate": 0.0002,
+      "loss": 1.0089,
+      "step": 1670
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.4851366877555847,
+      "learning_rate": 0.0002,
+      "loss": 1.0853,
+      "step": 1680
+    },
+    {
+      "epoch": 1.8500273672687466,
+      "grad_norm": 0.3262481391429901,
+      "learning_rate": 0.0002,
+      "loss": 0.9533,
+      "step": 1690
+    },
+    {
+      "epoch": 1.8609742747673783,
+      "grad_norm": 0.6904496550559998,
+      "learning_rate": 0.0002,
+      "loss": 1.048,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8719211822660098,
+      "grad_norm": 0.49789851903915405,
+      "learning_rate": 0.0002,
+      "loss": 1.0577,
+      "step": 1710
+    },
+    {
+      "epoch": 1.8828680897646415,
+      "grad_norm": 0.3035794198513031,
+      "learning_rate": 0.0002,
+      "loss": 1.0258,
+      "step": 1720
+    },
+    {
+      "epoch": 1.8938149972632732,
+      "grad_norm": 0.4588414430618286,
+      "learning_rate": 0.0002,
+      "loss": 0.9916,
+      "step": 1730
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.4313034117221832,
+      "learning_rate": 0.0002,
+      "loss": 0.9526,
+      "step": 1740
+    },
+    {
+      "epoch": 1.9157088122605364,
+      "grad_norm": 0.38562044501304626,
+      "learning_rate": 0.0002,
+      "loss": 1.0857,
+      "step": 1750
+    },
+    {
+      "epoch": 1.926655719759168,
+      "grad_norm": 0.46947410702705383,
+      "learning_rate": 0.0002,
+      "loss": 0.9763,
+      "step": 1760
+    },
+    {
+      "epoch": 1.9376026272577995,
+      "grad_norm": 0.3848404884338379,
+      "learning_rate": 0.0002,
+      "loss": 0.9967,
+      "step": 1770
+    },
+    {
+      "epoch": 1.9485495347564314,
+      "grad_norm": 0.30422744154930115,
+      "learning_rate": 0.0002,
+      "loss": 1.0474,
+      "step": 1780
+    },
+    {
+      "epoch": 1.959496442255063,
+      "grad_norm": 0.41100990772247314,
+      "learning_rate": 0.0002,
+      "loss": 1.022,
+      "step": 1790
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 0.3492335081100464,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9813902572523263,
+      "grad_norm": 0.364577978849411,
+      "learning_rate": 0.0002,
+      "loss": 0.9891,
+      "step": 1810
+    },
+    {
+      "epoch": 1.9923371647509578,
+      "grad_norm": 0.4312075674533844,
+      "learning_rate": 0.0002,
+      "loss": 1.0699,
+      "step": 1820
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.14472496509552,
+      "eval_runtime": 46.0786,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 1.194,
+      "step": 1827
+    },
+    {
+      "epoch": 2.0032840722495897,
+      "grad_norm": 0.5989689230918884,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 1830
+    },
+    {
+      "epoch": 2.014230979748221,
+      "grad_norm": 0.49720922112464905,
+      "learning_rate": 0.0002,
+      "loss": 0.9384,
+      "step": 1840
+    },
+    {
+      "epoch": 2.0251778872468527,
+      "grad_norm": 0.42675456404685974,
+      "learning_rate": 0.0002,
+      "loss": 0.8482,
+      "step": 1850
+    },
+    {
+      "epoch": 2.0361247947454846,
+      "grad_norm": 0.4637208580970764,
+      "learning_rate": 0.0002,
+      "loss": 0.8487,
+      "step": 1860
+    },
+    {
+      "epoch": 2.047071702244116,
+      "grad_norm": 0.8329976797103882,
+      "learning_rate": 0.0002,
+      "loss": 0.8212,
+      "step": 1870
+    },
+    {
+      "epoch": 2.0580186097427475,
+      "grad_norm": 0.7869427800178528,
+      "learning_rate": 0.0002,
+      "loss": 0.9547,
+      "step": 1880
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.4927455186843872,
+      "learning_rate": 0.0002,
+      "loss": 0.9351,
+      "step": 1890
+    },
+    {
+      "epoch": 2.079912424740011,
+      "grad_norm": 0.6264246702194214,
+      "learning_rate": 0.0002,
+      "loss": 0.8652,
+      "step": 1900
+    },
+    {
+      "epoch": 2.0908593322386424,
+      "grad_norm": 1.1164122819900513,
+      "learning_rate": 0.0002,
+      "loss": 0.9095,
+      "step": 1910
+    },
+    {
+      "epoch": 2.1018062397372743,
+      "grad_norm": 0.5283981561660767,
+      "learning_rate": 0.0002,
+      "loss": 0.7823,
+      "step": 1920
+    },
+    {
+      "epoch": 2.112753147235906,
+      "grad_norm": 0.45621731877326965,
+      "learning_rate": 0.0002,
+      "loss": 0.8065,
+      "step": 1930
+    },
+    {
+      "epoch": 2.1237000547345373,
+      "grad_norm": 1.381791591644287,
+      "learning_rate": 0.0002,
+      "loss": 0.9184,
+      "step": 1940
+    },
+    {
+      "epoch": 2.134646962233169,
+      "grad_norm": 0.5151259899139404,
+      "learning_rate": 0.0002,
+      "loss": 0.9006,
+      "step": 1950
+    },
+    {
+      "epoch": 2.1455938697318007,
+      "grad_norm": 0.9806339740753174,
+      "learning_rate": 0.0002,
+      "loss": 0.8436,
+      "step": 1960
+    },
+    {
+      "epoch": 2.1565407772304326,
+      "grad_norm": 0.4734154939651489,
+      "learning_rate": 0.0002,
+      "loss": 0.8749,
+      "step": 1970
+    },
+    {
+      "epoch": 2.167487684729064,
+      "grad_norm": 0.9553168416023254,
+      "learning_rate": 0.0002,
+      "loss": 0.9172,
+      "step": 1980
+    },
+    {
+      "epoch": 2.1784345922276955,
+      "grad_norm": 0.5895838141441345,
+      "learning_rate": 0.0002,
+      "loss": 0.8047,
+      "step": 1990
+    },
+    {
+      "epoch": 2.1893814997263275,
+      "grad_norm": 0.4488855302333832,
+      "learning_rate": 0.0002,
+      "loss": 0.7841,
+      "step": 2000
+    },
+    {
+      "epoch": 2.200328407224959,
+      "grad_norm": 1.0760235786437988,
+      "learning_rate": 0.0002,
+      "loss": 0.8205,
+      "step": 2010
+    },
+    {
+      "epoch": 2.2112753147235904,
+      "grad_norm": 0.5038785338401794,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 2020
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.59819495677948,
+      "learning_rate": 0.0002,
+      "loss": 0.8973,
+      "step": 2030
+    },
+    {
+      "epoch": 2.233169129720854,
+      "grad_norm": 0.5012075304985046,
+      "learning_rate": 0.0002,
+      "loss": 0.8009,
+      "step": 2040
+    },
+    {
+      "epoch": 2.2441160372194853,
+      "grad_norm": 0.44978439807891846,
+      "learning_rate": 0.0002,
+      "loss": 0.9087,
+      "step": 2050
+    },
+    {
+      "epoch": 2.255062944718117,
+      "grad_norm": 0.5350462198257446,
+      "learning_rate": 0.0002,
+      "loss": 0.823,
+      "step": 2060
+    },
+    {
+      "epoch": 2.2660098522167487,
+      "grad_norm": 0.6020669937133789,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 2070
+    },
+    {
+      "epoch": 2.2769567597153806,
+      "grad_norm": 0.5246821045875549,
+      "learning_rate": 0.0002,
+      "loss": 0.8023,
+      "step": 2080
+    },
+    {
+      "epoch": 2.287903667214012,
+      "grad_norm": 0.5711268782615662,
+      "learning_rate": 0.0002,
+      "loss": 0.8984,
+      "step": 2090
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.617317259311676,
+      "learning_rate": 0.0002,
+      "loss": 0.9093,
+      "step": 2100
+    },
+    {
+      "epoch": 2.3097974822112755,
+      "grad_norm": 0.8608947396278381,
+      "learning_rate": 0.0002,
+      "loss": 0.8311,
+      "step": 2110
+    },
+    {
+      "epoch": 2.320744389709907,
+      "grad_norm": 0.4739076793193817,
+      "learning_rate": 0.0002,
+      "loss": 0.7839,
+      "step": 2120
+    },
+    {
+      "epoch": 2.3316912972085384,
+      "grad_norm": 0.5538856983184814,
+      "learning_rate": 0.0002,
+      "loss": 0.84,
+      "step": 2130
+    },
+    {
+      "epoch": 2.3426382047071703,
+      "grad_norm": 0.6064935326576233,
+      "learning_rate": 0.0002,
+      "loss": 0.8994,
+      "step": 2140
+    },
+    {
+      "epoch": 2.353585112205802,
+      "grad_norm": 0.5019068121910095,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 2150
+    },
+    {
+      "epoch": 2.3645320197044333,
+      "grad_norm": 0.45340514183044434,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 2160
+    },
+    {
+      "epoch": 2.375478927203065,
+      "grad_norm": 0.7347203493118286,
+      "learning_rate": 0.0002,
+      "loss": 0.9254,
+      "step": 2170
+    },
+    {
+      "epoch": 2.3864258347016967,
+      "grad_norm": 0.46922534704208374,
+      "learning_rate": 0.0002,
+      "loss": 0.8507,
+      "step": 2180
+    },
+    {
+      "epoch": 2.3973727422003286,
+      "grad_norm": 0.5507845878601074,
+      "learning_rate": 0.0002,
+      "loss": 0.8325,
+      "step": 2190
+    },
+    {
+      "epoch": 2.40831964969896,
+      "grad_norm": 0.5621911883354187,
+      "learning_rate": 0.0002,
+      "loss": 0.8178,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4192665571975915,
+      "grad_norm": 0.5023514032363892,
+      "learning_rate": 0.0002,
+      "loss": 0.8569,
+      "step": 2210
+    },
+    {
+      "epoch": 2.4302134646962235,
+      "grad_norm": 0.6124861240386963,
+      "learning_rate": 0.0002,
+      "loss": 0.8355,
+      "step": 2220
+    },
+    {
+      "epoch": 2.441160372194855,
+      "grad_norm": 0.49614205956459045,
+      "learning_rate": 0.0002,
+      "loss": 0.885,
+      "step": 2230
+    },
+    {
+      "epoch": 2.4521072796934864,
+      "grad_norm": 0.6477900743484497,
+      "learning_rate": 0.0002,
+      "loss": 0.8008,
+      "step": 2240
+    },
+    {
+      "epoch": 2.4630541871921183,
+      "grad_norm": 0.5868843793869019,
+      "learning_rate": 0.0002,
+      "loss": 0.8622,
+      "step": 2250
+    },
+    {
+      "epoch": 2.47400109469075,
+      "grad_norm": 0.4364610016345978,
+      "learning_rate": 0.0002,
+      "loss": 0.8498,
+      "step": 2260
+    },
+    {
+      "epoch": 2.4849480021893813,
+      "grad_norm": 0.5792964696884155,
+      "learning_rate": 0.0002,
+      "loss": 0.8378,
+      "step": 2270
+    },
+    {
+      "epoch": 2.495894909688013,
+      "grad_norm": 0.5421269536018372,
+      "learning_rate": 0.0002,
+      "loss": 0.8743,
+      "step": 2280
+    },
+    {
+      "epoch": 2.5068418171866447,
+      "grad_norm": 0.5525493025779724,
+      "learning_rate": 0.0002,
+      "loss": 0.9637,
+      "step": 2290
+    },
+    {
+      "epoch": 2.5177887246852766,
+      "grad_norm": 0.6463850140571594,
+      "learning_rate": 0.0002,
+      "loss": 0.8075,
+      "step": 2300
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.6861311793327332,
+      "learning_rate": 0.0002,
+      "loss": 0.8591,
+      "step": 2310
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.5563555359840393,
+      "learning_rate": 0.0002,
+      "loss": 0.9287,
+      "step": 2320
+    },
+    {
+      "epoch": 2.5506294471811715,
+      "grad_norm": 0.5721169114112854,
+      "learning_rate": 0.0002,
+      "loss": 0.945,
+      "step": 2330
+    },
+    {
+      "epoch": 2.561576354679803,
+      "grad_norm": 0.5258274674415588,
+      "learning_rate": 0.0002,
+      "loss": 0.8271,
+      "step": 2340
+    },
+    {
+      "epoch": 2.572523262178435,
+      "grad_norm": 0.7057380676269531,
+      "learning_rate": 0.0002,
+      "loss": 0.8515,
+      "step": 2350
+    },
+    {
+      "epoch": 2.5834701696770663,
+      "grad_norm": 0.6869027614593506,
+      "learning_rate": 0.0002,
+      "loss": 0.8615,
+      "step": 2360
+    },
+    {
+      "epoch": 2.594417077175698,
+      "grad_norm": 0.4960809648036957,
+      "learning_rate": 0.0002,
+      "loss": 0.8043,
+      "step": 2370
+    },
+    {
+      "epoch": 2.6053639846743293,
+      "grad_norm": 0.9288380146026611,
+      "learning_rate": 0.0002,
+      "loss": 0.8476,
+      "step": 2380
+    },
+    {
+      "epoch": 2.616310892172961,
+      "grad_norm": 0.3765334188938141,
+      "learning_rate": 0.0002,
+      "loss": 0.873,
+      "step": 2390
+    },
+    {
+      "epoch": 2.6272577996715927,
+      "grad_norm": 0.7487865686416626,
+      "learning_rate": 0.0002,
+      "loss": 0.8764,
+      "step": 2400
+    },
+    {
+      "epoch": 2.6382047071702246,
+      "grad_norm": 0.6141156554222107,
+      "learning_rate": 0.0002,
+      "loss": 0.7577,
+      "step": 2410
+    },
+    {
+      "epoch": 2.649151614668856,
+      "grad_norm": 0.8420507907867432,
+      "learning_rate": 0.0002,
+      "loss": 0.8534,
+      "step": 2420
+    },
+    {
+      "epoch": 2.6600985221674875,
+      "grad_norm": 0.53386390209198,
+      "learning_rate": 0.0002,
+      "loss": 0.8311,
+      "step": 2430
+    },
+    {
+      "epoch": 2.6710454296661195,
+      "grad_norm": 0.5520607233047485,
+      "learning_rate": 0.0002,
+      "loss": 0.8486,
+      "step": 2440
+    },
+    {
+      "epoch": 2.681992337164751,
+      "grad_norm": 0.5337599515914917,
+      "learning_rate": 0.0002,
+      "loss": 0.8686,
+      "step": 2450
+    },
+    {
+      "epoch": 2.692939244663383,
+      "grad_norm": 0.48790836334228516,
+      "learning_rate": 0.0002,
+      "loss": 0.792,
+      "step": 2460
+    },
+    {
+      "epoch": 2.7038861521620143,
+      "grad_norm": 0.8287786245346069,
+      "learning_rate": 0.0002,
+      "loss": 0.7864,
+      "step": 2470
+    },
+    {
+      "epoch": 2.714833059660646,
+      "grad_norm": 0.5876168608665466,
+      "learning_rate": 0.0002,
+      "loss": 0.8244,
+      "step": 2480
+    },
+    {
+      "epoch": 2.7257799671592773,
+      "grad_norm": 0.5206760764122009,
+      "learning_rate": 0.0002,
+      "loss": 0.8773,
+      "step": 2490
+    },
+    {
+      "epoch": 2.736726874657909,
+      "grad_norm": 0.5619136691093445,
+      "learning_rate": 0.0002,
+      "loss": 0.8097,
+      "step": 2500
+    },
+    {
+      "epoch": 2.7476737821565407,
+      "grad_norm": 0.5614883899688721,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 2510
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.6157700419425964,
+      "learning_rate": 0.0002,
+      "loss": 0.8817,
+      "step": 2520
+    },
+    {
+      "epoch": 2.769567597153804,
+      "grad_norm": 0.5529953837394714,
+      "learning_rate": 0.0002,
+      "loss": 0.846,
+      "step": 2530
+    },
+    {
+      "epoch": 2.7805145046524355,
+      "grad_norm": 0.6731224060058594,
+      "learning_rate": 0.0002,
+      "loss": 0.8881,
+      "step": 2540
+    },
+    {
+      "epoch": 2.7914614121510675,
+      "grad_norm": 0.6960386633872986,
+      "learning_rate": 0.0002,
+      "loss": 0.9125,
+      "step": 2550
+    },
+    {
+      "epoch": 2.802408319649699,
+      "grad_norm": 0.5203493237495422,
+      "learning_rate": 0.0002,
+      "loss": 0.7823,
+      "step": 2560
+    },
+    {
+      "epoch": 2.813355227148331,
+      "grad_norm": 1.036837100982666,
+      "learning_rate": 0.0002,
+      "loss": 0.7951,
+      "step": 2570
+    },
+    {
+      "epoch": 2.8243021346469623,
+      "grad_norm": 0.6125805377960205,
+      "learning_rate": 0.0002,
+      "loss": 0.8427,
+      "step": 2580
+    },
+    {
+      "epoch": 2.835249042145594,
+      "grad_norm": 0.6298092603683472,
+      "learning_rate": 0.0002,
+      "loss": 0.8939,
+      "step": 2590
+    },
+    {
+      "epoch": 2.8461959496442253,
+      "grad_norm": 0.5882203578948975,
+      "learning_rate": 0.0002,
+      "loss": 0.8845,
+      "step": 2600
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.8619399666786194,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 2610
+    },
+    {
+      "epoch": 2.8680897646414887,
+      "grad_norm": 0.4722687304019928,
+      "learning_rate": 0.0002,
+      "loss": 0.8213,
+      "step": 2620
+    },
+    {
+      "epoch": 2.8790366721401206,
+      "grad_norm": 0.47399574518203735,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 2630
+    },
+    {
+      "epoch": 2.889983579638752,
+      "grad_norm": 0.5639172792434692,
+      "learning_rate": 0.0002,
+      "loss": 0.8325,
+      "step": 2640
+    },
+    {
+      "epoch": 2.9009304871373836,
+      "grad_norm": 0.4676816761493683,
+      "learning_rate": 0.0002,
+      "loss": 0.8653,
+      "step": 2650
+    },
+    {
+      "epoch": 2.9118773946360155,
+      "grad_norm": 0.6906291246414185,
+      "learning_rate": 0.0002,
+      "loss": 0.8966,
+      "step": 2660
+    },
+    {
+      "epoch": 2.922824302134647,
+      "grad_norm": 0.4369746148586273,
+      "learning_rate": 0.0002,
+      "loss": 0.8966,
+      "step": 2670
+    },
+    {
+      "epoch": 2.933771209633279,
+      "grad_norm": 0.46423083543777466,
+      "learning_rate": 0.0002,
+      "loss": 0.9173,
+      "step": 2680
+    },
+    {
+      "epoch": 2.9447181171319103,
+      "grad_norm": 0.5700525045394897,
+      "learning_rate": 0.0002,
+      "loss": 0.7961,
+      "step": 2690
+    },
+    {
+      "epoch": 2.955665024630542,
+      "grad_norm": 0.6221476793289185,
+      "learning_rate": 0.0002,
+      "loss": 0.8172,
+      "step": 2700
+    },
+    {
+      "epoch": 2.9666119321291733,
+      "grad_norm": 0.6102682948112488,
+      "learning_rate": 0.0002,
+      "loss": 0.8538,
+      "step": 2710
+    },
+    {
+      "epoch": 2.977558839627805,
+      "grad_norm": 0.5317878723144531,
+      "learning_rate": 0.0002,
+      "loss": 0.9779,
+      "step": 2720
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.4438510835170746,
+      "learning_rate": 0.0002,
+      "loss": 0.9314,
+      "step": 2730
+    },
+    {
+      "epoch": 2.9994526546250686,
+      "grad_norm": 0.5022130012512207,
+      "learning_rate": 0.0002,
+      "loss": 0.8553,
+      "step": 2740
+    },
+    {
+      "epoch": 2.9994526546250686,
+      "eval_loss": 1.1722838878631592,
+      "eval_runtime": 46.0829,
+      "eval_samples_per_second": 9.461,
+      "eval_steps_per_second": 1.194,
+      "step": 2740
+    },
+    {
+      "epoch": 3.0103995621237,
+      "grad_norm": 0.6384502053260803,
+      "learning_rate": 0.0002,
+      "loss": 0.6443,
+      "step": 2750
+    },
+    {
+      "epoch": 3.0213464696223316,
+      "grad_norm": 0.9928722381591797,
+      "learning_rate": 0.0002,
+      "loss": 0.7123,
+      "step": 2760
+    },
+    {
+      "epoch": 3.0322933771209635,
+      "grad_norm": 0.7813051342964172,
+      "learning_rate": 0.0002,
+      "loss": 0.6045,
+      "step": 2770
+    },
+    {
+      "epoch": 3.043240284619595,
+      "grad_norm": 1.0202556848526,
+      "learning_rate": 0.0002,
+      "loss": 0.6042,
+      "step": 2780
+    },
+    {
+      "epoch": 3.0541871921182264,
+      "grad_norm": 0.7581062316894531,
+      "learning_rate": 0.0002,
+      "loss": 0.6356,
+      "step": 2790
+    },
+    {
+      "epoch": 3.0651340996168583,
+      "grad_norm": 0.6252710223197937,
+      "learning_rate": 0.0002,
+      "loss": 0.6349,
+      "step": 2800
+    },
+    {
+      "epoch": 3.07608100711549,
+      "grad_norm": 0.7738662958145142,
+      "learning_rate": 0.0002,
+      "loss": 0.645,
+      "step": 2810
+    },
+    {
+      "epoch": 3.0870279146141213,
+      "grad_norm": 0.7381885051727295,
+      "learning_rate": 0.0002,
+      "loss": 0.627,
+      "step": 2820
+    },
+    {
+      "epoch": 3.097974822112753,
+      "grad_norm": 0.9197564721107483,
+      "learning_rate": 0.0002,
+      "loss": 0.6371,
+      "step": 2830
+    },
+    {
+      "epoch": 3.1089217296113847,
+      "grad_norm": 1.000976800918579,
+      "learning_rate": 0.0002,
+      "loss": 0.723,
+      "step": 2840
+    },
+    {
+      "epoch": 3.1198686371100166,
+      "grad_norm": 0.7559131383895874,
+      "learning_rate": 0.0002,
+      "loss": 0.6631,
+      "step": 2850
+    },
+    {
+      "epoch": 3.130815544608648,
+      "grad_norm": 0.7213780879974365,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 2860
+    },
+    {
+      "epoch": 3.1417624521072796,
+      "grad_norm": 0.945939838886261,
+      "learning_rate": 0.0002,
+      "loss": 0.6501,
+      "step": 2870
+    },
+    {
+      "epoch": 3.1527093596059115,
+      "grad_norm": 0.7277454137802124,
+      "learning_rate": 0.0002,
+      "loss": 0.6129,
+      "step": 2880
+    },
+    {
+      "epoch": 3.163656267104543,
+      "grad_norm": 0.762026846408844,
+      "learning_rate": 0.0002,
+      "loss": 0.6423,
+      "step": 2890
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.6471221446990967,
+      "learning_rate": 0.0002,
+      "loss": 0.5332,
+      "step": 2900
+    },
+    {
+      "epoch": 3.1855500821018063,
+      "grad_norm": 0.6018978357315063,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 2910
+    },
+    {
+      "epoch": 3.196496989600438,
+      "grad_norm": 0.8607320785522461,
+      "learning_rate": 0.0002,
+      "loss": 0.7274,
+      "step": 2920
+    },
+    {
+      "epoch": 3.2074438970990693,
+      "grad_norm": 0.8854126334190369,
+      "learning_rate": 0.0002,
+      "loss": 0.6139,
+      "step": 2930
+    },
+    {
+      "epoch": 3.218390804597701,
+      "grad_norm": 0.6620870232582092,
+      "learning_rate": 0.0002,
+      "loss": 0.6485,
+      "step": 2940
+    },
+    {
+      "epoch": 3.2293377120963327,
+      "grad_norm": 0.7377511858940125,
+      "learning_rate": 0.0002,
+      "loss": 0.6969,
+      "step": 2950
+    },
+    {
+      "epoch": 3.2402846195949646,
+      "grad_norm": 0.7803301811218262,
+      "learning_rate": 0.0002,
+      "loss": 0.6798,
+      "step": 2960
+    },
+    {
+      "epoch": 3.251231527093596,
+      "grad_norm": 0.834061861038208,
+      "learning_rate": 0.0002,
+      "loss": 0.6697,
+      "step": 2970
+    },
+    {
+      "epoch": 3.2621784345922276,
+      "grad_norm": 0.8496041893959045,
+      "learning_rate": 0.0002,
+      "loss": 0.6894,
+      "step": 2980
+    },
+    {
+      "epoch": 3.2731253420908595,
+      "grad_norm": 0.7967984676361084,
+      "learning_rate": 0.0002,
+      "loss": 0.6591,
+      "step": 2990
+    },
+    {
+      "epoch": 3.284072249589491,
+      "grad_norm": 1.0207016468048096,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 3000
+    },
+    {
+      "epoch": 3.2950191570881224,
+      "grad_norm": 0.7855771780014038,
+      "learning_rate": 0.0002,
+      "loss": 0.6586,
+      "step": 3010
+    },
+    {
+      "epoch": 3.3059660645867543,
+      "grad_norm": 0.9427546858787537,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 3020
+    },
+    {
+      "epoch": 3.316912972085386,
+      "grad_norm": 0.823542594909668,
+      "learning_rate": 0.0002,
+      "loss": 0.6277,
+      "step": 3030
+    },
+    {
+      "epoch": 3.3278598795840173,
+      "grad_norm": 0.9826635122299194,
+      "learning_rate": 0.0002,
+      "loss": 0.7109,
+      "step": 3040
+    },
+    {
+      "epoch": 3.338806787082649,
+      "grad_norm": 0.7259827852249146,
+      "learning_rate": 0.0002,
+      "loss": 0.6564,
+      "step": 3050
+    },
+    {
+      "epoch": 3.3497536945812807,
+      "grad_norm": 0.7774739861488342,
+      "learning_rate": 0.0002,
+      "loss": 0.653,
+      "step": 3060
+    },
+    {
+      "epoch": 3.3607006020799126,
+      "grad_norm": 0.7394293546676636,
+      "learning_rate": 0.0002,
+      "loss": 0.7529,
+      "step": 3070
+    },
+    {
+      "epoch": 3.371647509578544,
+      "grad_norm": 0.9017578959465027,
+      "learning_rate": 0.0002,
+      "loss": 0.5987,
+      "step": 3080
+    },
+    {
+      "epoch": 3.3825944170771756,
+      "grad_norm": 0.7451054453849792,
+      "learning_rate": 0.0002,
+      "loss": 0.6953,
+      "step": 3090
+    },
+    {
+      "epoch": 3.3935413245758075,
+      "grad_norm": 0.7321506142616272,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 3100
+    },
+    {
+      "epoch": 3.404488232074439,
+      "grad_norm": 0.6721828579902649,
+      "learning_rate": 0.0002,
+      "loss": 0.6555,
+      "step": 3110
+    },
+    {
+      "epoch": 3.4154351395730704,
+      "grad_norm": 0.774022102355957,
+      "learning_rate": 0.0002,
+      "loss": 0.6559,
+      "step": 3120
+    },
+    {
+      "epoch": 3.4263820470717024,
+      "grad_norm": 0.9143537282943726,
+      "learning_rate": 0.0002,
+      "loss": 0.7449,
+      "step": 3130
+    },
+    {
+      "epoch": 3.437328954570334,
+      "grad_norm": 1.226087212562561,
+      "learning_rate": 0.0002,
+      "loss": 0.6899,
+      "step": 3140
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.7545496225357056,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 3150
+    },
+    {
+      "epoch": 3.4592227695675972,
+      "grad_norm": 0.6515635848045349,
+      "learning_rate": 0.0002,
+      "loss": 0.6153,
+      "step": 3160
+    },
+    {
+      "epoch": 3.4701696770662287,
+      "grad_norm": 0.9297090172767639,
+      "learning_rate": 0.0002,
+      "loss": 0.6926,
+      "step": 3170
+    },
+    {
+      "epoch": 3.4811165845648606,
+      "grad_norm": 1.0130730867385864,
+      "learning_rate": 0.0002,
+      "loss": 0.6071,
+      "step": 3180
+    },
+    {
+      "epoch": 3.492063492063492,
+      "grad_norm": 0.7654589414596558,
+      "learning_rate": 0.0002,
+      "loss": 0.5959,
+      "step": 3190
+    },
+    {
+      "epoch": 3.5030103995621236,
+      "grad_norm": 0.9954977631568909,
+      "learning_rate": 0.0002,
+      "loss": 0.7401,
+      "step": 3200
+    },
+    {
+      "epoch": 3.5139573070607555,
+      "grad_norm": 0.6027487516403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6661,
+      "step": 3210
+    },
+    {
+      "epoch": 3.524904214559387,
+      "grad_norm": 0.741770327091217,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 3220
+    },
+    {
+      "epoch": 3.535851122058019,
+      "grad_norm": 1.0534909963607788,
+      "learning_rate": 0.0002,
+      "loss": 0.8112,
+      "step": 3230
+    },
+    {
+      "epoch": 3.5467980295566504,
+      "grad_norm": 0.937772274017334,
+      "learning_rate": 0.0002,
+      "loss": 0.6813,
+      "step": 3240
+    },
+    {
+      "epoch": 3.557744937055282,
+      "grad_norm": 0.8504213690757751,
+      "learning_rate": 0.0002,
+      "loss": 0.6681,
+      "step": 3250
+    },
+    {
+      "epoch": 3.5686918445539133,
+      "grad_norm": 0.7755007147789001,
+      "learning_rate": 0.0002,
+      "loss": 0.6436,
+      "step": 3260
+    },
+    {
+      "epoch": 3.5796387520525452,
+      "grad_norm": 1.0193358659744263,
+      "learning_rate": 0.0002,
+      "loss": 0.6213,
+      "step": 3270
+    },
+    {
+      "epoch": 3.5905856595511767,
+      "grad_norm": 0.8440536856651306,
+      "learning_rate": 0.0002,
+      "loss": 0.671,
+      "step": 3280
+    },
+    {
+      "epoch": 3.6015325670498086,
+      "grad_norm": 0.6195939183235168,
+      "learning_rate": 0.0002,
+      "loss": 0.6859,
+      "step": 3290
+    },
+    {
+      "epoch": 3.61247947454844,
+      "grad_norm": 0.8608590960502625,
+      "learning_rate": 0.0002,
+      "loss": 0.7446,
+      "step": 3300
+    },
+    {
+      "epoch": 3.6234263820470716,
+      "grad_norm": 0.6772327423095703,
+      "learning_rate": 0.0002,
+      "loss": 0.7301,
+      "step": 3310
+    },
+    {
+      "epoch": 3.6343732895457035,
+      "grad_norm": 0.8031839728355408,
+      "learning_rate": 0.0002,
+      "loss": 0.6298,
+      "step": 3320
+    },
+    {
+      "epoch": 3.645320197044335,
+      "grad_norm": 0.6080502271652222,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 3330
+    },
+    {
+      "epoch": 3.656267104542967,
+      "grad_norm": 0.8007240891456604,
+      "learning_rate": 0.0002,
+      "loss": 0.7431,
+      "step": 3340
+    },
+    {
+      "epoch": 3.6672140120415984,
+      "grad_norm": 0.8060704469680786,
+      "learning_rate": 0.0002,
+      "loss": 0.7446,
+      "step": 3350
+    },
+    {
+      "epoch": 3.67816091954023,
+      "grad_norm": 0.7547586560249329,
+      "learning_rate": 0.0002,
+      "loss": 0.6304,
+      "step": 3360
+    },
+    {
+      "epoch": 3.6891078270388613,
+      "grad_norm": 0.686851978302002,
+      "learning_rate": 0.0002,
+      "loss": 0.7066,
+      "step": 3370
+    },
+    {
+      "epoch": 3.7000547345374932,
+      "grad_norm": 0.9429075717926025,
+      "learning_rate": 0.0002,
+      "loss": 0.6748,
+      "step": 3380
+    },
+    {
+      "epoch": 3.7110016420361247,
+      "grad_norm": 0.7283591032028198,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 3390
+    },
+    {
+      "epoch": 3.7219485495347566,
+      "grad_norm": 0.8323085904121399,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 3400
+    },
+    {
+      "epoch": 3.732895457033388,
+      "grad_norm": 0.8529590964317322,
+      "learning_rate": 0.0002,
+      "loss": 0.7779,
+      "step": 3410
+    },
+    {
+      "epoch": 3.7438423645320196,
+      "grad_norm": 0.731752872467041,
+      "learning_rate": 0.0002,
+      "loss": 0.6555,
+      "step": 3420
+    },
+    {
+      "epoch": 3.7547892720306515,
+      "grad_norm": 0.8572278618812561,
+      "learning_rate": 0.0002,
+      "loss": 0.6928,
+      "step": 3430
+    },
+    {
+      "epoch": 3.765736179529283,
+      "grad_norm": 0.7408691048622131,
+      "learning_rate": 0.0002,
+      "loss": 0.6215,
+      "step": 3440
+    },
+    {
+      "epoch": 3.776683087027915,
+      "grad_norm": 0.7470445036888123,
+      "learning_rate": 0.0002,
+      "loss": 0.622,
+      "step": 3450
+    },
+    {
+      "epoch": 3.7876299945265464,
+      "grad_norm": 0.6806244254112244,
+      "learning_rate": 0.0002,
+      "loss": 0.7241,
+      "step": 3460
+    },
+    {
+      "epoch": 3.798576902025178,
+      "grad_norm": 0.9129069447517395,
+      "learning_rate": 0.0002,
+      "loss": 0.7739,
+      "step": 3470
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.8717501759529114,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 3480
+    },
+    {
+      "epoch": 3.8204707170224412,
+      "grad_norm": 0.6761979460716248,
+      "learning_rate": 0.0002,
+      "loss": 0.6188,
+      "step": 3490
+    },
+    {
+      "epoch": 3.8314176245210727,
+      "grad_norm": 1.0054380893707275,
+      "learning_rate": 0.0002,
+      "loss": 0.7601,
+      "step": 3500
+    },
+    {
+      "epoch": 3.8423645320197046,
+      "grad_norm": 1.1224009990692139,
+      "learning_rate": 0.0002,
+      "loss": 0.623,
+      "step": 3510
+    },
+    {
+      "epoch": 3.853311439518336,
+      "grad_norm": 0.8997692465782166,
+      "learning_rate": 0.0002,
+      "loss": 0.6918,
+      "step": 3520
+    },
+    {
+      "epoch": 3.8642583470169676,
+      "grad_norm": 1.0086902379989624,
+      "learning_rate": 0.0002,
+      "loss": 0.6357,
+      "step": 3530
+    },
+    {
+      "epoch": 3.8752052545155995,
+      "grad_norm": 0.772739589214325,
+      "learning_rate": 0.0002,
+      "loss": 0.6379,
+      "step": 3540
+    },
+    {
+      "epoch": 3.886152162014231,
+      "grad_norm": 1.211774230003357,
+      "learning_rate": 0.0002,
+      "loss": 0.7423,
+      "step": 3550
+    },
+    {
+      "epoch": 3.897099069512863,
+      "grad_norm": 0.9572356939315796,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 3560
+    },
+    {
+      "epoch": 3.9080459770114944,
+      "grad_norm": 0.7887842655181885,
+      "learning_rate": 0.0002,
+      "loss": 0.6836,
+      "step": 3570
+    },
+    {
+      "epoch": 3.918992884510126,
+      "grad_norm": 0.7308389544487,
+      "learning_rate": 0.0002,
+      "loss": 0.7576,
+      "step": 3580
+    },
+    {
+      "epoch": 3.9299397920087573,
+      "grad_norm": 1.0182650089263916,
+      "learning_rate": 0.0002,
+      "loss": 0.6001,
+      "step": 3590
+    },
+    {
+      "epoch": 3.9408866995073892,
+      "grad_norm": 0.8000147342681885,
+      "learning_rate": 0.0002,
+      "loss": 0.6942,
+      "step": 3600
+    },
+    {
+      "epoch": 3.9518336070060207,
+      "grad_norm": 0.7385728359222412,
+      "learning_rate": 0.0002,
+      "loss": 0.6244,
+      "step": 3610
+    },
+    {
+      "epoch": 3.9627805145046526,
+      "grad_norm": 0.9233261942863464,
+      "learning_rate": 0.0002,
+      "loss": 0.6718,
+      "step": 3620
+    },
+    {
+      "epoch": 3.973727422003284,
+      "grad_norm": 0.8486751914024353,
+      "learning_rate": 0.0002,
+      "loss": 0.6508,
+      "step": 3630
+    },
+    {
+      "epoch": 3.9846743295019156,
+      "grad_norm": 0.7593663334846497,
+      "learning_rate": 0.0002,
+      "loss": 0.6928,
+      "step": 3640
+    },
+    {
+      "epoch": 3.9956212370005475,
+      "grad_norm": 0.7885415554046631,
+      "learning_rate": 0.0002,
+      "loss": 0.6847,
+      "step": 3650
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.250312328338623,
+      "eval_runtime": 46.0842,
+      "eval_samples_per_second": 9.461,
+      "eval_steps_per_second": 1.193,
+      "step": 3654
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7304,
+  "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": 1.8768312652529664e+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-4/checkpoint-3654/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a158bca77bc6d58bfffd2acd2e9e641d481e1857fcbdd68fee875b74797abbc4
+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-4/checkpoint-4567/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-4/checkpoint-4567/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-4/checkpoint-4567/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690f0a108c96b12c41c037e7a8a073b10e97220dd5bf277ebaf85d1405a0e83a
+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-4/checkpoint-4567/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60d365e1ec200496f2cba711983f8608c9cb7d697c7c2b44a16f4348095ae96
+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-4/checkpoint-4567/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec7f713eac7d32af496212fbeebae513684ce562bcd5df63eb5603a6c82d35d
+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-4/checkpoint-4567/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81183db37481adb9d2771807b01e740317fdbbc85a4be1d990e73274e3f03be7
+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-4/checkpoint-4567/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-4/checkpoint-4567/tokenizer.json

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

gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-5885-sd-4/checkpoint-4567/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-4/checkpoint-4567/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
+}