Upload folder using huggingface_hub

.gitattributes

@@ -1444,3 +1444,12 @@ gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/checkpoint-82/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/checkpoint-99/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/README.md

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81567cf32cadbaf0117b7ad6c654a6b5fedc1775d91f1bdb0c88027d5c8d77d
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/README.md

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6473a088390d144a71fb5d6262cfcb03166ec6325101c01439b478ba9bbc7cda
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be363955abd87a9b2cd189b2be95ffb18b56117f04a81c7d102a2a60fe5bf62
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bd7fae2fa0cba607da0cb07a269842d7aefc88372e6504dbfbc5450fe150fd
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331d722674b800e8c81447e4ed79323e1d696462cdb1e33b3951468ac1e10380
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/special_tokens_map.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.model

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/trainer_state.json

@@ -0,0 +1,1071 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.535061483651072e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/README.md

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5255b8371af121ffd938ad3b296c11bf1b161f300e8b145036ba0aaa36da236e
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d06b6771d2ca9a49988d3e599bb788b097cb6f214f737a432c934551a4d6b6
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8108cffd99043e9b0dd148146f3f148b2da7a2ba7574bb45a7036fcb69d26b
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140316dec3419a0b494998a177826eeb12bf333a3620cbbec09475ff9aad2c93
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/special_tokens_map.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.model

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/trainer_state.json

@@ -0,0 +1,1597 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 2.9993183367416494,
+  "eval_steps": 10,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1302592225476608e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/README.md

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d322a6c4b731d65414a02fb7b29ee75b00db72c16e6c8653c71479e00fa0e1
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09e218b33248d7341dd93648fcfd8314302bc10aba9cad499e60cdb6caf4e77
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908b095cc2af9ec1c6d23f35a53f10a3767da3c4e2463cb3255296c45b67b341
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa0d97a46a5f131b267c442bd1fc27c085f03878ba83833c5fb8f7c8691b001
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/special_tokens_map.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.model

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/trainer_state.json

@@ -0,0 +1,2116 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 2934,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5070122967302144e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/README.md

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_config.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886255eb323b08886d2d430ad04a712afc30b8023f25ea26a3c02c6f10a9ab72
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5962bbcfb2896cdb8738e2c25f4ea65b58945ba973b1e5689d489e4b831f4e9
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c8dadd8ca3b2ae8518245449e0bbab16bc3271b1ac2e131fec9530a85f362c
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dd9f4175df7ddd0bf47bdd257e171fe3c9ae00d7e681fb5b6267fdcaf2677c
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/special_tokens_map.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.model

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

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer_config.json

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