diff --git a/.gitattributes b/.gitattributes
index 714b38b6c29461e77c2b5ca8e3ac7e6422e0c458..8e9018e1b737543e2b31a810421f8f9dfdbe97c2 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -488,3 +488,12 @@ gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_g
 gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-310-sd-10000/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-310-sd-10000/checkpoint-95/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-310-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80d9d474ec5f736ff6f891f0bc050cac2310e785
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546d9a50ec7778987fc8866c16760b7c1a04c7a6905e3f70f3124f1290485262
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a553d8d5bd48654e78c99dde9845367a20e8684b
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32b0ce88853c6a2901f885b5787f8bb1e9c7893c80060b860a6c18322d6481e
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5c6f5c8cd9c0819f65d4db8c14c771b603a0af0d
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f5a36986eeaa8880fb1846e49e2d0db34827d7c540cf8368c0cc74bc30439c
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e7e06f1207c51a011b1cc675862b027dc0050ba0
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63caed2314332795e1765ad356b005fd0aafff8aa84adc9b69d1976e6145414
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3f90f4683931460ef0a2748d22e850e81c371186
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132d0da63c27ed01e5000b359996ee7c08d48a2e6d697c47283001f811dc2e1a
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..63922fa50d2a5a4587810bdbd0cb0c5570f54e48
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/trainer_state.json
@@ -0,0 +1,816 @@
+{
+  "best_metric": 1.3988444805145264,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 1053,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    },
+    {
+      "epoch": 3.0199430199430197,
+      "grad_norm": 0.7109280228614807,
+      "learning_rate": 0.0002,
+      "loss": 1.3656,
+      "step": 530
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.6746246814727783,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 540
+    },
+    {
+      "epoch": 3.133903133903134,
+      "grad_norm": 0.7202523350715637,
+      "learning_rate": 0.0002,
+      "loss": 1.2685,
+      "step": 550
+    },
+    {
+      "epoch": 3.190883190883191,
+      "grad_norm": 0.697090208530426,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 560
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.7157464623451233,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 570
+    },
+    {
+      "epoch": 3.304843304843305,
+      "grad_norm": 0.8729232549667358,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 580
+    },
+    {
+      "epoch": 3.3618233618233617,
+      "grad_norm": 0.7119743227958679,
+      "learning_rate": 0.0002,
+      "loss": 1.2957,
+      "step": 590
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.7417448163032532,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 600
+    },
+    {
+      "epoch": 3.4757834757834756,
+      "grad_norm": 0.8174124956130981,
+      "learning_rate": 0.0002,
+      "loss": 1.2317,
+      "step": 610
+    },
+    {
+      "epoch": 3.532763532763533,
+      "grad_norm": 0.7199270129203796,
+      "learning_rate": 0.0002,
+      "loss": 1.2916,
+      "step": 620
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.989138662815094,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 630
+    },
+    {
+      "epoch": 3.646723646723647,
+      "grad_norm": 0.75921630859375,
+      "learning_rate": 0.0002,
+      "loss": 1.2263,
+      "step": 640
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.7844401001930237,
+      "learning_rate": 0.0002,
+      "loss": 1.2319,
+      "step": 650
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.9127110242843628,
+      "learning_rate": 0.0002,
+      "loss": 1.2851,
+      "step": 660
+    },
+    {
+      "epoch": 3.8176638176638176,
+      "grad_norm": 0.7972270846366882,
+      "learning_rate": 0.0002,
+      "loss": 1.2835,
+      "step": 670
+    },
+    {
+      "epoch": 3.8746438746438745,
+      "grad_norm": 0.7458992004394531,
+      "learning_rate": 0.0002,
+      "loss": 1.3105,
+      "step": 680
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.854924738407135,
+      "learning_rate": 0.0002,
+      "loss": 1.3017,
+      "step": 690
+    },
+    {
+      "epoch": 3.9886039886039883,
+      "grad_norm": 0.7763816118240356,
+      "learning_rate": 0.0002,
+      "loss": 1.2455,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3988444805145264,
+      "eval_runtime": 2.8697,
+      "eval_samples_per_second": 34.15,
+      "eval_steps_per_second": 4.53,
+      "step": 702
+    },
+    {
+      "epoch": 4.045584045584046,
+      "grad_norm": 0.877430260181427,
+      "learning_rate": 0.0002,
+      "loss": 1.178,
+      "step": 710
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.8365248441696167,
+      "learning_rate": 0.0002,
+      "loss": 1.1635,
+      "step": 720
+    },
+    {
+      "epoch": 4.15954415954416,
+      "grad_norm": 0.7748925089836121,
+      "learning_rate": 0.0002,
+      "loss": 1.2286,
+      "step": 730
+    },
+    {
+      "epoch": 4.216524216524217,
+      "grad_norm": 0.7695241570472717,
+      "learning_rate": 0.0002,
+      "loss": 1.1836,
+      "step": 740
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.7229928374290466,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 750
+    },
+    {
+      "epoch": 4.330484330484331,
+      "grad_norm": 0.7035910487174988,
+      "learning_rate": 0.0002,
+      "loss": 1.117,
+      "step": 760
+    },
+    {
+      "epoch": 4.387464387464387,
+      "grad_norm": 0.9075796008110046,
+      "learning_rate": 0.0002,
+      "loss": 1.189,
+      "step": 770
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.7957494854927063,
+      "learning_rate": 0.0002,
+      "loss": 1.1693,
+      "step": 780
+    },
+    {
+      "epoch": 4.501424501424501,
+      "grad_norm": 0.8733780384063721,
+      "learning_rate": 0.0002,
+      "loss": 1.1945,
+      "step": 790
+    },
+    {
+      "epoch": 4.5584045584045585,
+      "grad_norm": 0.8786619901657104,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.7101715803146362,
+      "learning_rate": 0.0002,
+      "loss": 1.185,
+      "step": 810
+    },
+    {
+      "epoch": 4.672364672364672,
+      "grad_norm": 0.7451328039169312,
+      "learning_rate": 0.0002,
+      "loss": 1.2063,
+      "step": 820
+    },
+    {
+      "epoch": 4.72934472934473,
+      "grad_norm": 0.7830713987350464,
+      "learning_rate": 0.0002,
+      "loss": 1.1939,
+      "step": 830
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 0.7804535031318665,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 840
+    },
+    {
+      "epoch": 4.843304843304844,
+      "grad_norm": 0.8121811747550964,
+      "learning_rate": 0.0002,
+      "loss": 1.2278,
+      "step": 850
+    },
+    {
+      "epoch": 4.9002849002849,
+      "grad_norm": 0.774864137172699,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 860
+    },
+    {
+      "epoch": 4.957264957264957,
+      "grad_norm": 0.7517814040184021,
+      "learning_rate": 0.0002,
+      "loss": 1.1736,
+      "step": 870
+    },
+    {
+      "epoch": 4.997150997150997,
+      "eval_loss": 1.4074795246124268,
+      "eval_runtime": 2.8707,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 4.529,
+      "step": 877
+    },
+    {
+      "epoch": 5.014245014245014,
+      "grad_norm": 0.7974972128868103,
+      "learning_rate": 0.0002,
+      "loss": 1.151,
+      "step": 880
+    },
+    {
+      "epoch": 5.071225071225071,
+      "grad_norm": 1.1127357482910156,
+      "learning_rate": 0.0002,
+      "loss": 1.0637,
+      "step": 890
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 0.8995195031166077,
+      "learning_rate": 0.0002,
+      "loss": 1.0497,
+      "step": 900
+    },
+    {
+      "epoch": 5.185185185185185,
+      "grad_norm": 0.8325890898704529,
+      "learning_rate": 0.0002,
+      "loss": 1.1101,
+      "step": 910
+    },
+    {
+      "epoch": 5.2421652421652425,
+      "grad_norm": 0.8830686807632446,
+      "learning_rate": 0.0002,
+      "loss": 1.0567,
+      "step": 920
+    },
+    {
+      "epoch": 5.299145299145299,
+      "grad_norm": 0.8856923580169678,
+      "learning_rate": 0.0002,
+      "loss": 1.1094,
+      "step": 930
+    },
+    {
+      "epoch": 5.356125356125356,
+      "grad_norm": 0.814587414264679,
+      "learning_rate": 0.0002,
+      "loss": 1.0328,
+      "step": 940
+    },
+    {
+      "epoch": 5.413105413105413,
+      "grad_norm": 0.9119254946708679,
+      "learning_rate": 0.0002,
+      "loss": 1.1379,
+      "step": 950
+    },
+    {
+      "epoch": 5.47008547008547,
+      "grad_norm": 0.8547661304473877,
+      "learning_rate": 0.0002,
+      "loss": 1.0993,
+      "step": 960
+    },
+    {
+      "epoch": 5.527065527065528,
+      "grad_norm": 0.943742036819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1137,
+      "step": 970
+    },
+    {
+      "epoch": 5.584045584045584,
+      "grad_norm": 1.1333340406417847,
+      "learning_rate": 0.0002,
+      "loss": 1.0815,
+      "step": 980
+    },
+    {
+      "epoch": 5.641025641025641,
+      "grad_norm": 1.0290982723236084,
+      "learning_rate": 0.0002,
+      "loss": 1.1161,
+      "step": 990
+    },
+    {
+      "epoch": 5.698005698005698,
+      "grad_norm": 1.0613716840744019,
+      "learning_rate": 0.0002,
+      "loss": 1.1477,
+      "step": 1000
+    },
+    {
+      "epoch": 5.754985754985755,
+      "grad_norm": 0.925118088722229,
+      "learning_rate": 0.0002,
+      "loss": 1.0878,
+      "step": 1010
+    },
+    {
+      "epoch": 5.811965811965812,
+      "grad_norm": 0.828220546245575,
+      "learning_rate": 0.0002,
+      "loss": 1.0658,
+      "step": 1020
+    },
+    {
+      "epoch": 5.868945868945869,
+      "grad_norm": 0.7466493248939514,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 1030
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.9189135432243347,
+      "learning_rate": 0.0002,
+      "loss": 1.1064,
+      "step": 1040
+    },
+    {
+      "epoch": 5.982905982905983,
+      "grad_norm": 0.9117513298988342,
+      "learning_rate": 0.0002,
+      "loss": 1.1114,
+      "step": 1050
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.4333235025405884,
+      "eval_runtime": 2.9267,
+      "eval_samples_per_second": 33.485,
+      "eval_steps_per_second": 4.442,
+      "step": 1053
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 1.2869762140864512e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1053/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bdf6e48cb33977258f81418f17a4249bbed05123
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb93bfb7a7e2f88be91722fe77b2e58951c3e881b76abab08aecfebca2193d2
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4f9be8f07aaff73ba4bd24f27ca279a8f3f5fc21
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c60cf797b395b8eea0213d2e932b1f07e9411bfa289d2649cd33a40be3e956d
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c451b7cfcfeea74502a26928ecf9f7cee9d3aa49
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24bcd1d38956feab07c380c0ddc0fe1495b1c01d06a77ff9f3a7ca576b5bbb6
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..617f0a8bdca03af1b48c2480aaac26a98874683e
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2510c124cf0764eadc4a791603e5beb4058d0b0e44bb1cbd79e4e0b8fb50e28d
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e097bf8fc4c12e1d4f403eb89e3e06c844c13990
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/trainer_state.json
@@ -0,0 +1,943 @@
+{
+  "best_metric": 1.3988444805145264,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702",
+  "epoch": 6.997150997150997,
+  "eval_steps": 10,
+  "global_step": 1228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    },
+    {
+      "epoch": 3.0199430199430197,
+      "grad_norm": 0.7109280228614807,
+      "learning_rate": 0.0002,
+      "loss": 1.3656,
+      "step": 530
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.6746246814727783,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 540
+    },
+    {
+      "epoch": 3.133903133903134,
+      "grad_norm": 0.7202523350715637,
+      "learning_rate": 0.0002,
+      "loss": 1.2685,
+      "step": 550
+    },
+    {
+      "epoch": 3.190883190883191,
+      "grad_norm": 0.697090208530426,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 560
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.7157464623451233,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 570
+    },
+    {
+      "epoch": 3.304843304843305,
+      "grad_norm": 0.8729232549667358,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 580
+    },
+    {
+      "epoch": 3.3618233618233617,
+      "grad_norm": 0.7119743227958679,
+      "learning_rate": 0.0002,
+      "loss": 1.2957,
+      "step": 590
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.7417448163032532,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 600
+    },
+    {
+      "epoch": 3.4757834757834756,
+      "grad_norm": 0.8174124956130981,
+      "learning_rate": 0.0002,
+      "loss": 1.2317,
+      "step": 610
+    },
+    {
+      "epoch": 3.532763532763533,
+      "grad_norm": 0.7199270129203796,
+      "learning_rate": 0.0002,
+      "loss": 1.2916,
+      "step": 620
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.989138662815094,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 630
+    },
+    {
+      "epoch": 3.646723646723647,
+      "grad_norm": 0.75921630859375,
+      "learning_rate": 0.0002,
+      "loss": 1.2263,
+      "step": 640
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.7844401001930237,
+      "learning_rate": 0.0002,
+      "loss": 1.2319,
+      "step": 650
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.9127110242843628,
+      "learning_rate": 0.0002,
+      "loss": 1.2851,
+      "step": 660
+    },
+    {
+      "epoch": 3.8176638176638176,
+      "grad_norm": 0.7972270846366882,
+      "learning_rate": 0.0002,
+      "loss": 1.2835,
+      "step": 670
+    },
+    {
+      "epoch": 3.8746438746438745,
+      "grad_norm": 0.7458992004394531,
+      "learning_rate": 0.0002,
+      "loss": 1.3105,
+      "step": 680
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.854924738407135,
+      "learning_rate": 0.0002,
+      "loss": 1.3017,
+      "step": 690
+    },
+    {
+      "epoch": 3.9886039886039883,
+      "grad_norm": 0.7763816118240356,
+      "learning_rate": 0.0002,
+      "loss": 1.2455,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3988444805145264,
+      "eval_runtime": 2.8697,
+      "eval_samples_per_second": 34.15,
+      "eval_steps_per_second": 4.53,
+      "step": 702
+    },
+    {
+      "epoch": 4.045584045584046,
+      "grad_norm": 0.877430260181427,
+      "learning_rate": 0.0002,
+      "loss": 1.178,
+      "step": 710
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.8365248441696167,
+      "learning_rate": 0.0002,
+      "loss": 1.1635,
+      "step": 720
+    },
+    {
+      "epoch": 4.15954415954416,
+      "grad_norm": 0.7748925089836121,
+      "learning_rate": 0.0002,
+      "loss": 1.2286,
+      "step": 730
+    },
+    {
+      "epoch": 4.216524216524217,
+      "grad_norm": 0.7695241570472717,
+      "learning_rate": 0.0002,
+      "loss": 1.1836,
+      "step": 740
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.7229928374290466,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 750
+    },
+    {
+      "epoch": 4.330484330484331,
+      "grad_norm": 0.7035910487174988,
+      "learning_rate": 0.0002,
+      "loss": 1.117,
+      "step": 760
+    },
+    {
+      "epoch": 4.387464387464387,
+      "grad_norm": 0.9075796008110046,
+      "learning_rate": 0.0002,
+      "loss": 1.189,
+      "step": 770
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.7957494854927063,
+      "learning_rate": 0.0002,
+      "loss": 1.1693,
+      "step": 780
+    },
+    {
+      "epoch": 4.501424501424501,
+      "grad_norm": 0.8733780384063721,
+      "learning_rate": 0.0002,
+      "loss": 1.1945,
+      "step": 790
+    },
+    {
+      "epoch": 4.5584045584045585,
+      "grad_norm": 0.8786619901657104,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.7101715803146362,
+      "learning_rate": 0.0002,
+      "loss": 1.185,
+      "step": 810
+    },
+    {
+      "epoch": 4.672364672364672,
+      "grad_norm": 0.7451328039169312,
+      "learning_rate": 0.0002,
+      "loss": 1.2063,
+      "step": 820
+    },
+    {
+      "epoch": 4.72934472934473,
+      "grad_norm": 0.7830713987350464,
+      "learning_rate": 0.0002,
+      "loss": 1.1939,
+      "step": 830
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 0.7804535031318665,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 840
+    },
+    {
+      "epoch": 4.843304843304844,
+      "grad_norm": 0.8121811747550964,
+      "learning_rate": 0.0002,
+      "loss": 1.2278,
+      "step": 850
+    },
+    {
+      "epoch": 4.9002849002849,
+      "grad_norm": 0.774864137172699,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 860
+    },
+    {
+      "epoch": 4.957264957264957,
+      "grad_norm": 0.7517814040184021,
+      "learning_rate": 0.0002,
+      "loss": 1.1736,
+      "step": 870
+    },
+    {
+      "epoch": 4.997150997150997,
+      "eval_loss": 1.4074795246124268,
+      "eval_runtime": 2.8707,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 4.529,
+      "step": 877
+    },
+    {
+      "epoch": 5.014245014245014,
+      "grad_norm": 0.7974972128868103,
+      "learning_rate": 0.0002,
+      "loss": 1.151,
+      "step": 880
+    },
+    {
+      "epoch": 5.071225071225071,
+      "grad_norm": 1.1127357482910156,
+      "learning_rate": 0.0002,
+      "loss": 1.0637,
+      "step": 890
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 0.8995195031166077,
+      "learning_rate": 0.0002,
+      "loss": 1.0497,
+      "step": 900
+    },
+    {
+      "epoch": 5.185185185185185,
+      "grad_norm": 0.8325890898704529,
+      "learning_rate": 0.0002,
+      "loss": 1.1101,
+      "step": 910
+    },
+    {
+      "epoch": 5.2421652421652425,
+      "grad_norm": 0.8830686807632446,
+      "learning_rate": 0.0002,
+      "loss": 1.0567,
+      "step": 920
+    },
+    {
+      "epoch": 5.299145299145299,
+      "grad_norm": 0.8856923580169678,
+      "learning_rate": 0.0002,
+      "loss": 1.1094,
+      "step": 930
+    },
+    {
+      "epoch": 5.356125356125356,
+      "grad_norm": 0.814587414264679,
+      "learning_rate": 0.0002,
+      "loss": 1.0328,
+      "step": 940
+    },
+    {
+      "epoch": 5.413105413105413,
+      "grad_norm": 0.9119254946708679,
+      "learning_rate": 0.0002,
+      "loss": 1.1379,
+      "step": 950
+    },
+    {
+      "epoch": 5.47008547008547,
+      "grad_norm": 0.8547661304473877,
+      "learning_rate": 0.0002,
+      "loss": 1.0993,
+      "step": 960
+    },
+    {
+      "epoch": 5.527065527065528,
+      "grad_norm": 0.943742036819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1137,
+      "step": 970
+    },
+    {
+      "epoch": 5.584045584045584,
+      "grad_norm": 1.1333340406417847,
+      "learning_rate": 0.0002,
+      "loss": 1.0815,
+      "step": 980
+    },
+    {
+      "epoch": 5.641025641025641,
+      "grad_norm": 1.0290982723236084,
+      "learning_rate": 0.0002,
+      "loss": 1.1161,
+      "step": 990
+    },
+    {
+      "epoch": 5.698005698005698,
+      "grad_norm": 1.0613716840744019,
+      "learning_rate": 0.0002,
+      "loss": 1.1477,
+      "step": 1000
+    },
+    {
+      "epoch": 5.754985754985755,
+      "grad_norm": 0.925118088722229,
+      "learning_rate": 0.0002,
+      "loss": 1.0878,
+      "step": 1010
+    },
+    {
+      "epoch": 5.811965811965812,
+      "grad_norm": 0.828220546245575,
+      "learning_rate": 0.0002,
+      "loss": 1.0658,
+      "step": 1020
+    },
+    {
+      "epoch": 5.868945868945869,
+      "grad_norm": 0.7466493248939514,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 1030
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.9189135432243347,
+      "learning_rate": 0.0002,
+      "loss": 1.1064,
+      "step": 1040
+    },
+    {
+      "epoch": 5.982905982905983,
+      "grad_norm": 0.9117513298988342,
+      "learning_rate": 0.0002,
+      "loss": 1.1114,
+      "step": 1050
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.4333235025405884,
+      "eval_runtime": 2.9267,
+      "eval_samples_per_second": 33.485,
+      "eval_steps_per_second": 4.442,
+      "step": 1053
+    },
+    {
+      "epoch": 6.0398860398860394,
+      "grad_norm": 0.9506599307060242,
+      "learning_rate": 0.0002,
+      "loss": 1.0368,
+      "step": 1060
+    },
+    {
+      "epoch": 6.096866096866097,
+      "grad_norm": 0.9809837937355042,
+      "learning_rate": 0.0002,
+      "loss": 1.0376,
+      "step": 1070
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.852557361125946,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 6.210826210826211,
+      "grad_norm": 1.135279893875122,
+      "learning_rate": 0.0002,
+      "loss": 0.9782,
+      "step": 1090
+    },
+    {
+      "epoch": 6.267806267806268,
+      "grad_norm": 1.0243879556655884,
+      "learning_rate": 0.0002,
+      "loss": 1.0238,
+      "step": 1100
+    },
+    {
+      "epoch": 6.3247863247863245,
+      "grad_norm": 0.9213914275169373,
+      "learning_rate": 0.0002,
+      "loss": 0.9815,
+      "step": 1110
+    },
+    {
+      "epoch": 6.381766381766382,
+      "grad_norm": 1.0042028427124023,
+      "learning_rate": 0.0002,
+      "loss": 0.9899,
+      "step": 1120
+    },
+    {
+      "epoch": 6.438746438746438,
+      "grad_norm": 1.1024253368377686,
+      "learning_rate": 0.0002,
+      "loss": 1.0249,
+      "step": 1130
+    },
+    {
+      "epoch": 6.495726495726496,
+      "grad_norm": 0.9245727062225342,
+      "learning_rate": 0.0002,
+      "loss": 1.0305,
+      "step": 1140
+    },
+    {
+      "epoch": 6.552706552706553,
+      "grad_norm": 0.8309272527694702,
+      "learning_rate": 0.0002,
+      "loss": 0.9766,
+      "step": 1150
+    },
+    {
+      "epoch": 6.60968660968661,
+      "grad_norm": 1.029746651649475,
+      "learning_rate": 0.0002,
+      "loss": 0.9945,
+      "step": 1160
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.9932991862297058,
+      "learning_rate": 0.0002,
+      "loss": 0.9955,
+      "step": 1170
+    },
+    {
+      "epoch": 6.7236467236467234,
+      "grad_norm": 1.1597973108291626,
+      "learning_rate": 0.0002,
+      "loss": 1.0808,
+      "step": 1180
+    },
+    {
+      "epoch": 6.780626780626781,
+      "grad_norm": 1.1373951435089111,
+      "learning_rate": 0.0002,
+      "loss": 1.0407,
+      "step": 1190
+    },
+    {
+      "epoch": 6.837606837606837,
+      "grad_norm": 1.0308297872543335,
+      "learning_rate": 0.0002,
+      "loss": 0.9513,
+      "step": 1200
+    },
+    {
+      "epoch": 6.894586894586895,
+      "grad_norm": 1.1555122137069702,
+      "learning_rate": 0.0002,
+      "loss": 1.0437,
+      "step": 1210
+    },
+    {
+      "epoch": 6.951566951566951,
+      "grad_norm": 0.9829897284507751,
+      "learning_rate": 0.0002,
+      "loss": 1.0164,
+      "step": 1220
+    },
+    {
+      "epoch": 6.997150997150997,
+      "eval_loss": 1.4769021272659302,
+      "eval_runtime": 2.8681,
+      "eval_samples_per_second": 34.168,
+      "eval_steps_per_second": 4.533,
+      "step": 1228
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 1.5014722497675264e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1228/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d121c52ad94233611614d0e57c905e1dcbf94a8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996ae93d058e24c4d884efc5bbe8a0ebf03d32679613e69751e8b35f5a890c82
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..427c8263cb86cb5b6ca641e1fbca7bf43c637f76
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b76e00ddd6519cf27006007fae304b2bc714f8d0062b99791ac01edb5b5373
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..df5d144b66ebf146c588b886982df2447a715376
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06598934139540514c1f935625f6d713bef5ba215b0be53186439cee2ecabd11
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9fe6273f6b6b7c1a6b30e659cc87ff6db7446315
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2651dbbb234a1169de9db4c1691e20ebcc2a6f2cad7a0b6f3fb47aa10c248f
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e1fdc734dc91d81029a310d2f14cdc232237e841
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/trainer_state.json
@@ -0,0 +1,1077 @@
+{
+  "best_metric": 1.3988444805145264,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702",
+  "epoch": 7.977207977207978,
+  "eval_steps": 10,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    },
+    {
+      "epoch": 3.0199430199430197,
+      "grad_norm": 0.7109280228614807,
+      "learning_rate": 0.0002,
+      "loss": 1.3656,
+      "step": 530
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.6746246814727783,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 540
+    },
+    {
+      "epoch": 3.133903133903134,
+      "grad_norm": 0.7202523350715637,
+      "learning_rate": 0.0002,
+      "loss": 1.2685,
+      "step": 550
+    },
+    {
+      "epoch": 3.190883190883191,
+      "grad_norm": 0.697090208530426,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 560
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.7157464623451233,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 570
+    },
+    {
+      "epoch": 3.304843304843305,
+      "grad_norm": 0.8729232549667358,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 580
+    },
+    {
+      "epoch": 3.3618233618233617,
+      "grad_norm": 0.7119743227958679,
+      "learning_rate": 0.0002,
+      "loss": 1.2957,
+      "step": 590
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.7417448163032532,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 600
+    },
+    {
+      "epoch": 3.4757834757834756,
+      "grad_norm": 0.8174124956130981,
+      "learning_rate": 0.0002,
+      "loss": 1.2317,
+      "step": 610
+    },
+    {
+      "epoch": 3.532763532763533,
+      "grad_norm": 0.7199270129203796,
+      "learning_rate": 0.0002,
+      "loss": 1.2916,
+      "step": 620
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.989138662815094,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 630
+    },
+    {
+      "epoch": 3.646723646723647,
+      "grad_norm": 0.75921630859375,
+      "learning_rate": 0.0002,
+      "loss": 1.2263,
+      "step": 640
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.7844401001930237,
+      "learning_rate": 0.0002,
+      "loss": 1.2319,
+      "step": 650
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.9127110242843628,
+      "learning_rate": 0.0002,
+      "loss": 1.2851,
+      "step": 660
+    },
+    {
+      "epoch": 3.8176638176638176,
+      "grad_norm": 0.7972270846366882,
+      "learning_rate": 0.0002,
+      "loss": 1.2835,
+      "step": 670
+    },
+    {
+      "epoch": 3.8746438746438745,
+      "grad_norm": 0.7458992004394531,
+      "learning_rate": 0.0002,
+      "loss": 1.3105,
+      "step": 680
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.854924738407135,
+      "learning_rate": 0.0002,
+      "loss": 1.3017,
+      "step": 690
+    },
+    {
+      "epoch": 3.9886039886039883,
+      "grad_norm": 0.7763816118240356,
+      "learning_rate": 0.0002,
+      "loss": 1.2455,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3988444805145264,
+      "eval_runtime": 2.8697,
+      "eval_samples_per_second": 34.15,
+      "eval_steps_per_second": 4.53,
+      "step": 702
+    },
+    {
+      "epoch": 4.045584045584046,
+      "grad_norm": 0.877430260181427,
+      "learning_rate": 0.0002,
+      "loss": 1.178,
+      "step": 710
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.8365248441696167,
+      "learning_rate": 0.0002,
+      "loss": 1.1635,
+      "step": 720
+    },
+    {
+      "epoch": 4.15954415954416,
+      "grad_norm": 0.7748925089836121,
+      "learning_rate": 0.0002,
+      "loss": 1.2286,
+      "step": 730
+    },
+    {
+      "epoch": 4.216524216524217,
+      "grad_norm": 0.7695241570472717,
+      "learning_rate": 0.0002,
+      "loss": 1.1836,
+      "step": 740
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.7229928374290466,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 750
+    },
+    {
+      "epoch": 4.330484330484331,
+      "grad_norm": 0.7035910487174988,
+      "learning_rate": 0.0002,
+      "loss": 1.117,
+      "step": 760
+    },
+    {
+      "epoch": 4.387464387464387,
+      "grad_norm": 0.9075796008110046,
+      "learning_rate": 0.0002,
+      "loss": 1.189,
+      "step": 770
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.7957494854927063,
+      "learning_rate": 0.0002,
+      "loss": 1.1693,
+      "step": 780
+    },
+    {
+      "epoch": 4.501424501424501,
+      "grad_norm": 0.8733780384063721,
+      "learning_rate": 0.0002,
+      "loss": 1.1945,
+      "step": 790
+    },
+    {
+      "epoch": 4.5584045584045585,
+      "grad_norm": 0.8786619901657104,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.7101715803146362,
+      "learning_rate": 0.0002,
+      "loss": 1.185,
+      "step": 810
+    },
+    {
+      "epoch": 4.672364672364672,
+      "grad_norm": 0.7451328039169312,
+      "learning_rate": 0.0002,
+      "loss": 1.2063,
+      "step": 820
+    },
+    {
+      "epoch": 4.72934472934473,
+      "grad_norm": 0.7830713987350464,
+      "learning_rate": 0.0002,
+      "loss": 1.1939,
+      "step": 830
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 0.7804535031318665,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 840
+    },
+    {
+      "epoch": 4.843304843304844,
+      "grad_norm": 0.8121811747550964,
+      "learning_rate": 0.0002,
+      "loss": 1.2278,
+      "step": 850
+    },
+    {
+      "epoch": 4.9002849002849,
+      "grad_norm": 0.774864137172699,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 860
+    },
+    {
+      "epoch": 4.957264957264957,
+      "grad_norm": 0.7517814040184021,
+      "learning_rate": 0.0002,
+      "loss": 1.1736,
+      "step": 870
+    },
+    {
+      "epoch": 4.997150997150997,
+      "eval_loss": 1.4074795246124268,
+      "eval_runtime": 2.8707,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 4.529,
+      "step": 877
+    },
+    {
+      "epoch": 5.014245014245014,
+      "grad_norm": 0.7974972128868103,
+      "learning_rate": 0.0002,
+      "loss": 1.151,
+      "step": 880
+    },
+    {
+      "epoch": 5.071225071225071,
+      "grad_norm": 1.1127357482910156,
+      "learning_rate": 0.0002,
+      "loss": 1.0637,
+      "step": 890
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 0.8995195031166077,
+      "learning_rate": 0.0002,
+      "loss": 1.0497,
+      "step": 900
+    },
+    {
+      "epoch": 5.185185185185185,
+      "grad_norm": 0.8325890898704529,
+      "learning_rate": 0.0002,
+      "loss": 1.1101,
+      "step": 910
+    },
+    {
+      "epoch": 5.2421652421652425,
+      "grad_norm": 0.8830686807632446,
+      "learning_rate": 0.0002,
+      "loss": 1.0567,
+      "step": 920
+    },
+    {
+      "epoch": 5.299145299145299,
+      "grad_norm": 0.8856923580169678,
+      "learning_rate": 0.0002,
+      "loss": 1.1094,
+      "step": 930
+    },
+    {
+      "epoch": 5.356125356125356,
+      "grad_norm": 0.814587414264679,
+      "learning_rate": 0.0002,
+      "loss": 1.0328,
+      "step": 940
+    },
+    {
+      "epoch": 5.413105413105413,
+      "grad_norm": 0.9119254946708679,
+      "learning_rate": 0.0002,
+      "loss": 1.1379,
+      "step": 950
+    },
+    {
+      "epoch": 5.47008547008547,
+      "grad_norm": 0.8547661304473877,
+      "learning_rate": 0.0002,
+      "loss": 1.0993,
+      "step": 960
+    },
+    {
+      "epoch": 5.527065527065528,
+      "grad_norm": 0.943742036819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1137,
+      "step": 970
+    },
+    {
+      "epoch": 5.584045584045584,
+      "grad_norm": 1.1333340406417847,
+      "learning_rate": 0.0002,
+      "loss": 1.0815,
+      "step": 980
+    },
+    {
+      "epoch": 5.641025641025641,
+      "grad_norm": 1.0290982723236084,
+      "learning_rate": 0.0002,
+      "loss": 1.1161,
+      "step": 990
+    },
+    {
+      "epoch": 5.698005698005698,
+      "grad_norm": 1.0613716840744019,
+      "learning_rate": 0.0002,
+      "loss": 1.1477,
+      "step": 1000
+    },
+    {
+      "epoch": 5.754985754985755,
+      "grad_norm": 0.925118088722229,
+      "learning_rate": 0.0002,
+      "loss": 1.0878,
+      "step": 1010
+    },
+    {
+      "epoch": 5.811965811965812,
+      "grad_norm": 0.828220546245575,
+      "learning_rate": 0.0002,
+      "loss": 1.0658,
+      "step": 1020
+    },
+    {
+      "epoch": 5.868945868945869,
+      "grad_norm": 0.7466493248939514,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 1030
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.9189135432243347,
+      "learning_rate": 0.0002,
+      "loss": 1.1064,
+      "step": 1040
+    },
+    {
+      "epoch": 5.982905982905983,
+      "grad_norm": 0.9117513298988342,
+      "learning_rate": 0.0002,
+      "loss": 1.1114,
+      "step": 1050
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.4333235025405884,
+      "eval_runtime": 2.9267,
+      "eval_samples_per_second": 33.485,
+      "eval_steps_per_second": 4.442,
+      "step": 1053
+    },
+    {
+      "epoch": 6.0398860398860394,
+      "grad_norm": 0.9506599307060242,
+      "learning_rate": 0.0002,
+      "loss": 1.0368,
+      "step": 1060
+    },
+    {
+      "epoch": 6.096866096866097,
+      "grad_norm": 0.9809837937355042,
+      "learning_rate": 0.0002,
+      "loss": 1.0376,
+      "step": 1070
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.852557361125946,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 6.210826210826211,
+      "grad_norm": 1.135279893875122,
+      "learning_rate": 0.0002,
+      "loss": 0.9782,
+      "step": 1090
+    },
+    {
+      "epoch": 6.267806267806268,
+      "grad_norm": 1.0243879556655884,
+      "learning_rate": 0.0002,
+      "loss": 1.0238,
+      "step": 1100
+    },
+    {
+      "epoch": 6.3247863247863245,
+      "grad_norm": 0.9213914275169373,
+      "learning_rate": 0.0002,
+      "loss": 0.9815,
+      "step": 1110
+    },
+    {
+      "epoch": 6.381766381766382,
+      "grad_norm": 1.0042028427124023,
+      "learning_rate": 0.0002,
+      "loss": 0.9899,
+      "step": 1120
+    },
+    {
+      "epoch": 6.438746438746438,
+      "grad_norm": 1.1024253368377686,
+      "learning_rate": 0.0002,
+      "loss": 1.0249,
+      "step": 1130
+    },
+    {
+      "epoch": 6.495726495726496,
+      "grad_norm": 0.9245727062225342,
+      "learning_rate": 0.0002,
+      "loss": 1.0305,
+      "step": 1140
+    },
+    {
+      "epoch": 6.552706552706553,
+      "grad_norm": 0.8309272527694702,
+      "learning_rate": 0.0002,
+      "loss": 0.9766,
+      "step": 1150
+    },
+    {
+      "epoch": 6.60968660968661,
+      "grad_norm": 1.029746651649475,
+      "learning_rate": 0.0002,
+      "loss": 0.9945,
+      "step": 1160
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.9932991862297058,
+      "learning_rate": 0.0002,
+      "loss": 0.9955,
+      "step": 1170
+    },
+    {
+      "epoch": 6.7236467236467234,
+      "grad_norm": 1.1597973108291626,
+      "learning_rate": 0.0002,
+      "loss": 1.0808,
+      "step": 1180
+    },
+    {
+      "epoch": 6.780626780626781,
+      "grad_norm": 1.1373951435089111,
+      "learning_rate": 0.0002,
+      "loss": 1.0407,
+      "step": 1190
+    },
+    {
+      "epoch": 6.837606837606837,
+      "grad_norm": 1.0308297872543335,
+      "learning_rate": 0.0002,
+      "loss": 0.9513,
+      "step": 1200
+    },
+    {
+      "epoch": 6.894586894586895,
+      "grad_norm": 1.1555122137069702,
+      "learning_rate": 0.0002,
+      "loss": 1.0437,
+      "step": 1210
+    },
+    {
+      "epoch": 6.951566951566951,
+      "grad_norm": 0.9829897284507751,
+      "learning_rate": 0.0002,
+      "loss": 1.0164,
+      "step": 1220
+    },
+    {
+      "epoch": 6.997150997150997,
+      "eval_loss": 1.4769021272659302,
+      "eval_runtime": 2.8681,
+      "eval_samples_per_second": 34.168,
+      "eval_steps_per_second": 4.533,
+      "step": 1228
+    },
+    {
+      "epoch": 7.0085470085470085,
+      "grad_norm": 1.1083747148513794,
+      "learning_rate": 0.0002,
+      "loss": 1.0111,
+      "step": 1230
+    },
+    {
+      "epoch": 7.065527065527066,
+      "grad_norm": 1.1454236507415771,
+      "learning_rate": 0.0002,
+      "loss": 0.9179,
+      "step": 1240
+    },
+    {
+      "epoch": 7.122507122507122,
+      "grad_norm": 0.9501869082450867,
+      "learning_rate": 0.0002,
+      "loss": 0.9271,
+      "step": 1250
+    },
+    {
+      "epoch": 7.17948717948718,
+      "grad_norm": 1.2393906116485596,
+      "learning_rate": 0.0002,
+      "loss": 0.9121,
+      "step": 1260
+    },
+    {
+      "epoch": 7.236467236467236,
+      "grad_norm": 1.0671173334121704,
+      "learning_rate": 0.0002,
+      "loss": 0.9396,
+      "step": 1270
+    },
+    {
+      "epoch": 7.293447293447294,
+      "grad_norm": 1.1026686429977417,
+      "learning_rate": 0.0002,
+      "loss": 0.9023,
+      "step": 1280
+    },
+    {
+      "epoch": 7.35042735042735,
+      "grad_norm": 1.2422044277191162,
+      "learning_rate": 0.0002,
+      "loss": 0.9267,
+      "step": 1290
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 1.0772203207015991,
+      "learning_rate": 0.0002,
+      "loss": 0.8394,
+      "step": 1300
+    },
+    {
+      "epoch": 7.464387464387464,
+      "grad_norm": 1.1025265455245972,
+      "learning_rate": 0.0002,
+      "loss": 0.9361,
+      "step": 1310
+    },
+    {
+      "epoch": 7.521367521367521,
+      "grad_norm": 1.0232294797897339,
+      "learning_rate": 0.0002,
+      "loss": 0.9124,
+      "step": 1320
+    },
+    {
+      "epoch": 7.578347578347579,
+      "grad_norm": 1.2126119136810303,
+      "learning_rate": 0.0002,
+      "loss": 0.9412,
+      "step": 1330
+    },
+    {
+      "epoch": 7.635327635327635,
+      "grad_norm": 1.2359609603881836,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1340
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 0.9109336733818054,
+      "learning_rate": 0.0002,
+      "loss": 0.9096,
+      "step": 1350
+    },
+    {
+      "epoch": 7.749287749287749,
+      "grad_norm": 1.0734586715698242,
+      "learning_rate": 0.0002,
+      "loss": 0.9038,
+      "step": 1360
+    },
+    {
+      "epoch": 7.806267806267806,
+      "grad_norm": 1.1725562810897827,
+      "learning_rate": 0.0002,
+      "loss": 0.9674,
+      "step": 1370
+    },
+    {
+      "epoch": 7.863247863247864,
+      "grad_norm": 1.0173115730285645,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 1380
+    },
+    {
+      "epoch": 7.92022792022792,
+      "grad_norm": 1.0145931243896484,
+      "learning_rate": 0.0002,
+      "loss": 0.9764,
+      "step": 1390
+    },
+    {
+      "epoch": 7.977207977207978,
+      "grad_norm": 1.1547255516052246,
+      "learning_rate": 0.0002,
+      "loss": 0.9465,
+      "step": 1400
+    },
+    {
+      "epoch": 7.977207977207978,
+      "eval_loss": 1.5259032249450684,
+      "eval_runtime": 2.8665,
+      "eval_samples_per_second": 34.189,
+      "eval_steps_per_second": 4.535,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.71107948691456e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-1400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fc174897662e5a692779f0f708e0cda5d77e39e3
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ec3539bb63b004a8819781d7ee42f59196664959c3f96f1ab42d86c713a717
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b4175c1b99e36b87d9e80060927404f66320bf19
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce19ebf7d1e6646f94c988c8db0232e74aaaea6babb0872e5423307daca571b8
+size 15064250
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1c0ed90489248e7ac384a04e150a4db06c9c8f7a
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f090d858199d2cc9c083d07c2e4899a2a9a85efb05bcd4868287516cefc9c8b
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a3cb9ccfbedab0c2b791dd5b35ef0ae8496e5e6d
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17c000dd3ad474c8365253b4464489310fed0d13c745556138280174b380deb
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b6ab2774f5c2b910b64868dbdbdf808ad933e676
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/trainer_state.json
@@ -0,0 +1,160 @@
+{
+  "best_metric": 1.4962449073791504,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175",
+  "epoch": 0.9971509971509972,
+  "eval_steps": 10,
+  "global_step": 175,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 2144960356810752.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d2b6bf68533babf434280fb052413bcdef9eb90e
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d249baadd7651f7480915719016860aef236570aeedec487dc11b8d432d039
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e4237567d52573fb5f9d5e2764c7eb5b41f1ac80
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5bd17bd9391440d9e8c57167a588644b70c0688e8ae291d9b27d230ebf3581
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..63e8fc1ec9b451877e8036d4d0e6f04ed3819843
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e825d2d493326d56e7a45471324ee3b2edc3a2c29ab8a7f6c8152c7611cda758
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..178095c7b1952d590ca5225131b0dae21e2643c8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2b853507ab2cbae6ba6a48164491c149815ca5c0f4c12284692bd9b767467a
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ccd5a13abbf1c9df28220a38d8953453cc5c38ed
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/trainer_state.json
@@ -0,0 +1,294 @@
+{
+  "best_metric": 1.424173355102539,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 4289920713621504.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3917978d9c857cc851f6bc3ee07c32b090a8c17d
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2c14d1164da88ac3058a635806ea1e8a6fd34d0a1740a1484b459000951abd
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c452658d157bcb4cfe70f9a5c4e1b2b566e94303
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c078d52f77a571c3b9c0243421b8658607190f2293f80966b16c91d32b266b62
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9b4223e7259dc680cefcf73fd7abff7e2a4aa560
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307b37840034606c696e089402057d30a6c66307ce18f592ce232bf34835d6e5
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..82dfb9562a61df80e93d3b55101d8d010c7c3121
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0990c2b37525fb7ec7cdb410f81507a201ecde29c679ebc72b310be6b98d228a
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa66fe41a3f9b3220b922f2bccfebc4e9ccc38cf
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/trainer_state.json
@@ -0,0 +1,421 @@
+{
+  "best_metric": 1.401209831237793,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526",
+  "epoch": 2.9971509971509973,
+  "eval_steps": 10,
+  "global_step": 526,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 6434881070432256.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80d9d474ec5f736ff6f891f0bc050cac2310e785
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546d9a50ec7778987fc8866c16760b7c1a04c7a6905e3f70f3124f1290485262
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..54ac8e4bfa4a70523fc4e4f75bb07d902aa949ce
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848e06c0d4fe2ed0b179b537b7e7766309fcd5fce160dfe7e269d7de3bcd0e4c
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..136189d5d7d1c22526ef4c427bde12e0b26030f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca35e8cac13f2c7c0d021c4d01e2143654afb68b4c8ed46fe69f129cd919b1bb
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bd8417267b16219ee5a126567055b12f32886f6f
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e995849b9c6ab36aa64065dd7fc5a77b3083bec77091ba5e6b0df9e813f35c
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..43fed2a40667e3025d84e3201e3e33a097f907d8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/trainer_state.json
@@ -0,0 +1,555 @@
+{
+  "best_metric": 1.3988444805145264,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 702,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    },
+    {
+      "epoch": 3.0199430199430197,
+      "grad_norm": 0.7109280228614807,
+      "learning_rate": 0.0002,
+      "loss": 1.3656,
+      "step": 530
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.6746246814727783,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 540
+    },
+    {
+      "epoch": 3.133903133903134,
+      "grad_norm": 0.7202523350715637,
+      "learning_rate": 0.0002,
+      "loss": 1.2685,
+      "step": 550
+    },
+    {
+      "epoch": 3.190883190883191,
+      "grad_norm": 0.697090208530426,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 560
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.7157464623451233,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 570
+    },
+    {
+      "epoch": 3.304843304843305,
+      "grad_norm": 0.8729232549667358,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 580
+    },
+    {
+      "epoch": 3.3618233618233617,
+      "grad_norm": 0.7119743227958679,
+      "learning_rate": 0.0002,
+      "loss": 1.2957,
+      "step": 590
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.7417448163032532,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 600
+    },
+    {
+      "epoch": 3.4757834757834756,
+      "grad_norm": 0.8174124956130981,
+      "learning_rate": 0.0002,
+      "loss": 1.2317,
+      "step": 610
+    },
+    {
+      "epoch": 3.532763532763533,
+      "grad_norm": 0.7199270129203796,
+      "learning_rate": 0.0002,
+      "loss": 1.2916,
+      "step": 620
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.989138662815094,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 630
+    },
+    {
+      "epoch": 3.646723646723647,
+      "grad_norm": 0.75921630859375,
+      "learning_rate": 0.0002,
+      "loss": 1.2263,
+      "step": 640
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.7844401001930237,
+      "learning_rate": 0.0002,
+      "loss": 1.2319,
+      "step": 650
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.9127110242843628,
+      "learning_rate": 0.0002,
+      "loss": 1.2851,
+      "step": 660
+    },
+    {
+      "epoch": 3.8176638176638176,
+      "grad_norm": 0.7972270846366882,
+      "learning_rate": 0.0002,
+      "loss": 1.2835,
+      "step": 670
+    },
+    {
+      "epoch": 3.8746438746438745,
+      "grad_norm": 0.7458992004394531,
+      "learning_rate": 0.0002,
+      "loss": 1.3105,
+      "step": 680
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.854924738407135,
+      "learning_rate": 0.0002,
+      "loss": 1.3017,
+      "step": 690
+    },
+    {
+      "epoch": 3.9886039886039883,
+      "grad_norm": 0.7763816118240356,
+      "learning_rate": 0.0002,
+      "loss": 1.2455,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3988444805145264,
+      "eval_runtime": 2.8697,
+      "eval_samples_per_second": 34.15,
+      "eval_steps_per_second": 4.53,
+      "step": 702
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 8579841427243008.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/README.md b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2b-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
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e99bbcd43df1c19d98706c7e3be95c93844c5349
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_model.safetensors b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6b24065ea732fb5439cb5c8e8aae5b6bf9d48248
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5b54df0064fd4f7487437063888bd353dca3025c8b5b6025f1fc6094b7e0fc
+size 29500848
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/optimizer.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2256972aca723ac83bc09610aaa23a9b635d0e72
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d934bfca6f8c7a03c6f843ec96dd8afa5c13d8385e15c15e8883e6bbe5f65a
+size 15064314
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/rng_state.pth b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a5e21f47c1f351d24254ecb09fb4697626a31c79
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47813bb1b8f9cea460a57067389c6476843c238ca8e482b1f48ee269de4cbc8
+size 14244
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/scheduler.pt b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04bcb6bcf40f85183359e1b7fc68c5f525d8046b
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bbe98cd388d0aef05bda7399971fbd5ee2093cb9bfaaef8acc8327f92a107a
+size 1064
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/trainer_state.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8007591b8ad6ea51b5020b018351e2cbd3118045
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/trainer_state.json
@@ -0,0 +1,682 @@
+{
+  "best_metric": 1.3988444805145264,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702",
+  "epoch": 4.997150997150997,
+  "eval_steps": 10,
+  "global_step": 877,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05698005698005698,
+      "grad_norm": 1.0227872133255005,
+      "learning_rate": 0.0002,
+      "loss": 3.5896,
+      "step": 10
+    },
+    {
+      "epoch": 0.11396011396011396,
+      "grad_norm": 3.86788010597229,
+      "learning_rate": 0.0002,
+      "loss": 2.5124,
+      "step": 20
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 1.3474394083023071,
+      "learning_rate": 0.0002,
+      "loss": 2.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 1.1816296577453613,
+      "learning_rate": 0.0002,
+      "loss": 2.0115,
+      "step": 40
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.0907047986984253,
+      "learning_rate": 0.0002,
+      "loss": 1.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.9163471460342407,
+      "learning_rate": 0.0002,
+      "loss": 1.8608,
+      "step": 60
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "grad_norm": 1.0441275835037231,
+      "learning_rate": 0.0002,
+      "loss": 1.7334,
+      "step": 70
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "grad_norm": 1.0836364030838013,
+      "learning_rate": 0.0002,
+      "loss": 1.6496,
+      "step": 80
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.5817112922668457,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 90
+    },
+    {
+      "epoch": 0.5698005698005698,
+      "grad_norm": 0.8991169929504395,
+      "learning_rate": 0.0002,
+      "loss": 1.6697,
+      "step": 100
+    },
+    {
+      "epoch": 0.6267806267806267,
+      "grad_norm": 1.1820793151855469,
+      "learning_rate": 0.0002,
+      "loss": 1.621,
+      "step": 110
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.8205533623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.6376,
+      "step": 120
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.8154979348182678,
+      "learning_rate": 0.0002,
+      "loss": 1.5902,
+      "step": 130
+    },
+    {
+      "epoch": 0.7977207977207977,
+      "grad_norm": 0.7292681336402893,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 140
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.7737869024276733,
+      "learning_rate": 0.0002,
+      "loss": 1.6554,
+      "step": 150
+    },
+    {
+      "epoch": 0.9116809116809117,
+      "grad_norm": 0.7786843180656433,
+      "learning_rate": 0.0002,
+      "loss": 1.4696,
+      "step": 160
+    },
+    {
+      "epoch": 0.9686609686609686,
+      "grad_norm": 0.6918405294418335,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 170
+    },
+    {
+      "epoch": 0.9971509971509972,
+      "eval_loss": 1.4962449073791504,
+      "eval_runtime": 2.869,
+      "eval_samples_per_second": 34.158,
+      "eval_steps_per_second": 4.531,
+      "step": 175
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.6754891872406006,
+      "learning_rate": 0.0002,
+      "loss": 1.5305,
+      "step": 180
+    },
+    {
+      "epoch": 1.0826210826210827,
+      "grad_norm": 0.6875350475311279,
+      "learning_rate": 0.0002,
+      "loss": 1.4709,
+      "step": 190
+    },
+    {
+      "epoch": 1.1396011396011396,
+      "grad_norm": 0.7870411276817322,
+      "learning_rate": 0.0002,
+      "loss": 1.4744,
+      "step": 200
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.6934282779693604,
+      "learning_rate": 0.0002,
+      "loss": 1.5414,
+      "step": 210
+    },
+    {
+      "epoch": 1.2535612535612537,
+      "grad_norm": 0.6980162858963013,
+      "learning_rate": 0.0002,
+      "loss": 1.5129,
+      "step": 220
+    },
+    {
+      "epoch": 1.3105413105413106,
+      "grad_norm": 0.6163203120231628,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 230
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.5967347025871277,
+      "learning_rate": 0.0002,
+      "loss": 1.4028,
+      "step": 240
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 0.7622564435005188,
+      "learning_rate": 0.0002,
+      "loss": 1.4945,
+      "step": 250
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6667674779891968,
+      "learning_rate": 0.0002,
+      "loss": 1.4426,
+      "step": 260
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.9225417971611023,
+      "learning_rate": 0.0002,
+      "loss": 1.4227,
+      "step": 270
+    },
+    {
+      "epoch": 1.5954415954415955,
+      "grad_norm": 0.6473053097724915,
+      "learning_rate": 0.0002,
+      "loss": 1.3687,
+      "step": 280
+    },
+    {
+      "epoch": 1.6524216524216524,
+      "grad_norm": 0.8250042796134949,
+      "learning_rate": 0.0002,
+      "loss": 1.5086,
+      "step": 290
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.6660609841346741,
+      "learning_rate": 0.0002,
+      "loss": 1.4259,
+      "step": 300
+    },
+    {
+      "epoch": 1.7663817663817665,
+      "grad_norm": 0.7542873620986938,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 310
+    },
+    {
+      "epoch": 1.8233618233618234,
+      "grad_norm": 0.5261648297309875,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 320
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.6519118547439575,
+      "learning_rate": 0.0002,
+      "loss": 1.4251,
+      "step": 330
+    },
+    {
+      "epoch": 1.9373219373219372,
+      "grad_norm": 0.7584664821624756,
+      "learning_rate": 0.0002,
+      "loss": 1.3613,
+      "step": 340
+    },
+    {
+      "epoch": 1.9943019943019942,
+      "grad_norm": 0.6466017365455627,
+      "learning_rate": 0.0002,
+      "loss": 1.4797,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.424173355102539,
+      "eval_runtime": 2.8659,
+      "eval_samples_per_second": 34.195,
+      "eval_steps_per_second": 4.536,
+      "step": 351
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.7457601428031921,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 360
+    },
+    {
+      "epoch": 2.1082621082621085,
+      "grad_norm": 0.6645848751068115,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "step": 370
+    },
+    {
+      "epoch": 2.1652421652421654,
+      "grad_norm": 0.6545299887657166,
+      "learning_rate": 0.0002,
+      "loss": 1.3244,
+      "step": 380
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7429937124252319,
+      "learning_rate": 0.0002,
+      "loss": 1.4025,
+      "step": 390
+    },
+    {
+      "epoch": 2.2792022792022792,
+      "grad_norm": 0.6929682493209839,
+      "learning_rate": 0.0002,
+      "loss": 1.3995,
+      "step": 400
+    },
+    {
+      "epoch": 2.336182336182336,
+      "grad_norm": 0.6999889016151428,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 410
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.7174718379974365,
+      "learning_rate": 0.0002,
+      "loss": 1.3573,
+      "step": 420
+    },
+    {
+      "epoch": 2.45014245014245,
+      "grad_norm": 0.667317807674408,
+      "learning_rate": 0.0002,
+      "loss": 1.3169,
+      "step": 430
+    },
+    {
+      "epoch": 2.5071225071225074,
+      "grad_norm": 0.8981409072875977,
+      "learning_rate": 0.0002,
+      "loss": 1.3877,
+      "step": 440
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.7560263872146606,
+      "learning_rate": 0.0002,
+      "loss": 1.3085,
+      "step": 450
+    },
+    {
+      "epoch": 2.6210826210826212,
+      "grad_norm": 0.699364185333252,
+      "learning_rate": 0.0002,
+      "loss": 1.278,
+      "step": 460
+    },
+    {
+      "epoch": 2.678062678062678,
+      "grad_norm": 0.666292667388916,
+      "learning_rate": 0.0002,
+      "loss": 1.2962,
+      "step": 470
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.7564692497253418,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 480
+    },
+    {
+      "epoch": 2.792022792022792,
+      "grad_norm": 0.7561964392662048,
+      "learning_rate": 0.0002,
+      "loss": 1.3489,
+      "step": 490
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.6506860852241516,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 500
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.6425383687019348,
+      "learning_rate": 0.0002,
+      "loss": 1.311,
+      "step": 510
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.7424822449684143,
+      "learning_rate": 0.0002,
+      "loss": 1.2879,
+      "step": 520
+    },
+    {
+      "epoch": 2.9971509971509973,
+      "eval_loss": 1.401209831237793,
+      "eval_runtime": 2.8721,
+      "eval_samples_per_second": 34.121,
+      "eval_steps_per_second": 4.526,
+      "step": 526
+    },
+    {
+      "epoch": 3.0199430199430197,
+      "grad_norm": 0.7109280228614807,
+      "learning_rate": 0.0002,
+      "loss": 1.3656,
+      "step": 530
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.6746246814727783,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 540
+    },
+    {
+      "epoch": 3.133903133903134,
+      "grad_norm": 0.7202523350715637,
+      "learning_rate": 0.0002,
+      "loss": 1.2685,
+      "step": 550
+    },
+    {
+      "epoch": 3.190883190883191,
+      "grad_norm": 0.697090208530426,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 560
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.7157464623451233,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 570
+    },
+    {
+      "epoch": 3.304843304843305,
+      "grad_norm": 0.8729232549667358,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 580
+    },
+    {
+      "epoch": 3.3618233618233617,
+      "grad_norm": 0.7119743227958679,
+      "learning_rate": 0.0002,
+      "loss": 1.2957,
+      "step": 590
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.7417448163032532,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 600
+    },
+    {
+      "epoch": 3.4757834757834756,
+      "grad_norm": 0.8174124956130981,
+      "learning_rate": 0.0002,
+      "loss": 1.2317,
+      "step": 610
+    },
+    {
+      "epoch": 3.532763532763533,
+      "grad_norm": 0.7199270129203796,
+      "learning_rate": 0.0002,
+      "loss": 1.2916,
+      "step": 620
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.989138662815094,
+      "learning_rate": 0.0002,
+      "loss": 1.2074,
+      "step": 630
+    },
+    {
+      "epoch": 3.646723646723647,
+      "grad_norm": 0.75921630859375,
+      "learning_rate": 0.0002,
+      "loss": 1.2263,
+      "step": 640
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.7844401001930237,
+      "learning_rate": 0.0002,
+      "loss": 1.2319,
+      "step": 650
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.9127110242843628,
+      "learning_rate": 0.0002,
+      "loss": 1.2851,
+      "step": 660
+    },
+    {
+      "epoch": 3.8176638176638176,
+      "grad_norm": 0.7972270846366882,
+      "learning_rate": 0.0002,
+      "loss": 1.2835,
+      "step": 670
+    },
+    {
+      "epoch": 3.8746438746438745,
+      "grad_norm": 0.7458992004394531,
+      "learning_rate": 0.0002,
+      "loss": 1.3105,
+      "step": 680
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.854924738407135,
+      "learning_rate": 0.0002,
+      "loss": 1.3017,
+      "step": 690
+    },
+    {
+      "epoch": 3.9886039886039883,
+      "grad_norm": 0.7763816118240356,
+      "learning_rate": 0.0002,
+      "loss": 1.2455,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3988444805145264,
+      "eval_runtime": 2.8697,
+      "eval_samples_per_second": 34.15,
+      "eval_steps_per_second": 4.53,
+      "step": 702
+    },
+    {
+      "epoch": 4.045584045584046,
+      "grad_norm": 0.877430260181427,
+      "learning_rate": 0.0002,
+      "loss": 1.178,
+      "step": 710
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.8365248441696167,
+      "learning_rate": 0.0002,
+      "loss": 1.1635,
+      "step": 720
+    },
+    {
+      "epoch": 4.15954415954416,
+      "grad_norm": 0.7748925089836121,
+      "learning_rate": 0.0002,
+      "loss": 1.2286,
+      "step": 730
+    },
+    {
+      "epoch": 4.216524216524217,
+      "grad_norm": 0.7695241570472717,
+      "learning_rate": 0.0002,
+      "loss": 1.1836,
+      "step": 740
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.7229928374290466,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 750
+    },
+    {
+      "epoch": 4.330484330484331,
+      "grad_norm": 0.7035910487174988,
+      "learning_rate": 0.0002,
+      "loss": 1.117,
+      "step": 760
+    },
+    {
+      "epoch": 4.387464387464387,
+      "grad_norm": 0.9075796008110046,
+      "learning_rate": 0.0002,
+      "loss": 1.189,
+      "step": 770
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.7957494854927063,
+      "learning_rate": 0.0002,
+      "loss": 1.1693,
+      "step": 780
+    },
+    {
+      "epoch": 4.501424501424501,
+      "grad_norm": 0.8733780384063721,
+      "learning_rate": 0.0002,
+      "loss": 1.1945,
+      "step": 790
+    },
+    {
+      "epoch": 4.5584045584045585,
+      "grad_norm": 0.8786619901657104,
+      "learning_rate": 0.0002,
+      "loss": 1.1867,
+      "step": 800
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.7101715803146362,
+      "learning_rate": 0.0002,
+      "loss": 1.185,
+      "step": 810
+    },
+    {
+      "epoch": 4.672364672364672,
+      "grad_norm": 0.7451328039169312,
+      "learning_rate": 0.0002,
+      "loss": 1.2063,
+      "step": 820
+    },
+    {
+      "epoch": 4.72934472934473,
+      "grad_norm": 0.7830713987350464,
+      "learning_rate": 0.0002,
+      "loss": 1.1939,
+      "step": 830
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 0.7804535031318665,
+      "learning_rate": 0.0002,
+      "loss": 1.1251,
+      "step": 840
+    },
+    {
+      "epoch": 4.843304843304844,
+      "grad_norm": 0.8121811747550964,
+      "learning_rate": 0.0002,
+      "loss": 1.2278,
+      "step": 850
+    },
+    {
+      "epoch": 4.9002849002849,
+      "grad_norm": 0.774864137172699,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 860
+    },
+    {
+      "epoch": 4.957264957264957,
+      "grad_norm": 0.7517814040184021,
+      "learning_rate": 0.0002,
+      "loss": 1.1736,
+      "step": 870
+    },
+    {
+      "epoch": 4.997150997150997,
+      "eval_loss": 1.4074795246124268,
+      "eval_runtime": 2.8707,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 4.529,
+      "step": 877
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1400,
+  "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": 1.072480178405376e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-877/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/special_tokens_map.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/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
+  }
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
+size 34356041
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.model b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer_config.json b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/tokenizer_config.json
@@ -0,0 +1,1757 @@
+{
+  "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
+    }
+  },
+  "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
+}
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_args.bin b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d5855b60b1cd520479d619dcdb51a31eb8d4e70
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8913d560553d015fae1642e2e67f5097556e650cbd6fe1331d7f7e47624aa
+size 5560
diff --git a/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_log.jsonl b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..a969a67d2351636ad02ffdd9a9c8b5b4efc07881
--- /dev/null
+++ b/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/training_log.jsonl
@@ -0,0 +1,23 @@
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 226.64873790740967, "total_accumulated_duration": 226.64873790740967, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5884, "grad_norm": 1.0246449708938599, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5087, "grad_norm": 4.416985034942627, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1383, "grad_norm": 1.339896321296692, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0126, "grad_norm": 1.1955891847610474, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8748, "grad_norm": 1.5392284393310547, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.864, "grad_norm": 2.2324352264404297, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7324, "grad_norm": 0.883982241153717, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6497, "grad_norm": 0.8040387630462646, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.581, "grad_norm": 0.6630058288574219, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.8256624341011047, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6244, "grad_norm": 1.7843570709228516, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6385, "grad_norm": 0.7624598741531372, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5932, "grad_norm": 0.8000739216804504, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6153, "grad_norm": 0.746695876121521, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6538, "grad_norm": 0.7385406494140625, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4707, "grad_norm": 0.7716621160507202, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5073, "grad_norm": 0.6918502449989319, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 228.30274987220764, "total_accumulated_duration": 228.30274987220764, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5887, "grad_norm": 1.0285680294036865, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5088, "grad_norm": 4.263883113861084, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1316, "grad_norm": 1.319510579109192, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0138, "grad_norm": 1.172463297843933, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8757, "grad_norm": 1.2299168109893799, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8628, "grad_norm": 1.8571380376815796, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7331, "grad_norm": 0.8769466876983643, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6501, "grad_norm": 0.9425599575042725, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5829, "grad_norm": 0.6939888000488281, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6745, "grad_norm": 0.80997234582901, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6317, "grad_norm": 0.576340913772583, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6426, "grad_norm": 0.8277338743209839, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5979, "grad_norm": 0.812319278717041, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6206, "grad_norm": 0.744087815284729, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.658, "grad_norm": 0.7455664277076721, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4727, "grad_norm": 0.7555345892906189, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.508, "grad_norm": 0.6886737942695618, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 196.87817358970642, "total_accumulated_duration": 196.87817358970642, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5888, "grad_norm": 1.02470064163208, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5103, "grad_norm": 4.141382217407227, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1431, "grad_norm": 1.3427177667617798, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2450870275497437, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.873, "grad_norm": 0.8380146026611328, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8602, "grad_norm": 1.6974546909332275, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7297, "grad_norm": 0.842096209526062, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6483, "grad_norm": 0.8819207549095154, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5822, "grad_norm": 0.6970117688179016, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6723, "grad_norm": 0.732140839099884, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6293, "grad_norm": 0.6692239046096802, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6398, "grad_norm": 0.8081008195877075, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5955, "grad_norm": 0.8078020215034485, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6184, "grad_norm": 0.752601683139801, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.657, "grad_norm": 0.7533067464828491, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.472, "grad_norm": 0.7555228471755981, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5078, "grad_norm": 0.6797512769699097, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 196.1910490989685, "total_accumulated_duration": 196.1910490989685, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5867, "grad_norm": 1.0275089740753174, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5071, "grad_norm": 5.149324893951416, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1403, "grad_norm": 1.302829384803772, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0171, "grad_norm": 1.2056041955947876, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.877, "grad_norm": 1.6039173603057861, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8654, "grad_norm": 2.2578282356262207, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7336, "grad_norm": 0.891614556312561, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6502, "grad_norm": 0.7235773205757141, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5805, "grad_norm": 0.5928594470024109, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6703, "grad_norm": 0.9899774789810181, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6212, "grad_norm": 0.8848198056221008, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6381, "grad_norm": 0.8585798144340515, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5921, "grad_norm": 0.849170446395874, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6146, "grad_norm": 0.7267282605171204, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6543, "grad_norm": 0.7717547416687012, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4709, "grad_norm": 0.7685355544090271, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5076, "grad_norm": 0.6848856210708618, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 183.86725306510925, "total_accumulated_duration": 183.86725306510925, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5898, "grad_norm": 1.0211373567581177, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5123, "grad_norm": 3.9195690155029297, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1553, "grad_norm": 1.3422091007232666, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0102, "grad_norm": 1.2220985889434814, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8759, "grad_norm": 0.7786314487457275, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8629, "grad_norm": 1.8703639507293701, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.731, "grad_norm": 0.8601687550544739, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6498, "grad_norm": 0.839336633682251, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5831, "grad_norm": 0.6838223338127136, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.671, "grad_norm": 0.736075222492218, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.626, "grad_norm": 1.5018651485443115, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6381, "grad_norm": 0.7694732546806335, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5935, "grad_norm": 0.7978103756904602, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6163, "grad_norm": 0.7607526779174805, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6548, "grad_norm": 0.7390126585960388, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4711, "grad_norm": 0.7577585577964783, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5073, "grad_norm": 0.7028831839561462, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 196.93704557418823, "total_accumulated_duration": 196.93704557418823, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5874, "grad_norm": 1.0230627059936523, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5078, "grad_norm": 4.167836666107178, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1285, "grad_norm": 1.3116984367370605, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0141, "grad_norm": 1.1505714654922485, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8763, "grad_norm": 1.017291784286499, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8617, "grad_norm": 1.3579925298690796, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7338, "grad_norm": 0.9080680012702942, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0459669828414917, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5827, "grad_norm": 0.6726023554801941, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6734, "grad_norm": 0.7067064046859741, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6281, "grad_norm": 1.1829911470413208, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6394, "grad_norm": 0.7684104442596436, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5943, "grad_norm": 0.8014359474182129, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6178, "grad_norm": 0.7519007325172424, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6557, "grad_norm": 0.7420642375946045, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4719, "grad_norm": 0.7634224891662598, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5076, "grad_norm": 0.6824071407318115, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 197.5335237979889, "total_accumulated_duration": 197.5335237979889, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5873, "grad_norm": 1.025920033454895, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5064, "grad_norm": 4.992947578430176, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1384, "grad_norm": 1.3070180416107178, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0151, "grad_norm": 1.200543999671936, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8758, "grad_norm": 1.6544991731643677, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8644, "grad_norm": 2.260460138320923, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7332, "grad_norm": 0.8998034596443176, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6499, "grad_norm": 0.7905030250549316, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5811, "grad_norm": 0.630607545375824, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6711, "grad_norm": 0.9616371393203735, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.6229, "grad_norm": 1.5203739404678345, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6378, "grad_norm": 0.8046877980232239, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5926, "grad_norm": 0.8209801316261292, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6151, "grad_norm": 0.7339947819709778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6543, "grad_norm": 0.7577587962150574, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7635911703109741, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5068, "grad_norm": 0.6860561966896057, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 73.26114892959595, "total_accumulated_duration": 73.26114892959595, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 0.9971509971509972, "step": 175, "epoch_duration": 72.66727685928345, "total_accumulated_duration": 72.66727685928345, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 5628.7490234375}, "avg_memory_reserved": {"GPU_0": 6182.0}, "peak_memory_reserved": {"GPU_0": 6182.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}]}
+{"epoch": 2.0, "step": 351, "epoch_duration": 72.60998892784119, "total_accumulated_duration": 145.87113785743713, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}]}
+{"epoch": 2.0, "step": 351, "epoch_duration": 74.16440558433533, "total_accumulated_duration": 146.83168244361877, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-175", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}]}
+{"epoch": 2.9971509971509973, "step": 526, "epoch_duration": 74.01644945144653, "total_accumulated_duration": 219.88758730888367, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}]}
+{"epoch": 2.9971509971509973, "step": 526, "epoch_duration": 73.78220868110657, "total_accumulated_duration": 220.61389112472534, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-351", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}]}
+{"epoch": 4.0, "step": 702, "epoch_duration": 71.99642825126648, "total_accumulated_duration": 291.88401556015015, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.4021576642990112, "eval_runtime": 2.8786, "eval_samples_per_second": 34.044, "eval_steps_per_second": 4.516, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3666, "grad_norm": 0.7116469144821167, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2579, "grad_norm": 0.6635934114456177, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2688, "grad_norm": 0.7347352504730225, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1805, "grad_norm": 0.693499743938446, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2463, "grad_norm": 0.7138662934303284, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2412, "grad_norm": 0.8807587027549744, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2961, "grad_norm": 0.7191319465637207, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2778, "grad_norm": 0.7447595596313477, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2302, "grad_norm": 0.7865943312644958, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2871, "grad_norm": 0.713374674320221, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2054, "grad_norm": 0.9345150589942932, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.758057713508606, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.78746497631073, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2881, "grad_norm": 0.9097195267677307, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2845, "grad_norm": 0.7972307205200195, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3123, "grad_norm": 0.7442638278007507, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3008, "grad_norm": 0.836273193359375, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2444, "grad_norm": 0.7712854146957397, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}]}
+{"epoch": 4.0, "step": 702, "epoch_duration": 73.55654525756836, "total_accumulated_duration": 294.1704363822937, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-526", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.401209831237793, "eval_runtime": 2.8721, "eval_samples_per_second": 34.121, "eval_steps_per_second": 4.526, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3656, "grad_norm": 0.7109280228614807, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2571, "grad_norm": 0.6746246814727783, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2685, "grad_norm": 0.7202523350715637, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1808, "grad_norm": 0.697090208530426, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2479, "grad_norm": 0.7157464623451233, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2426, "grad_norm": 0.8729232549667358, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2957, "grad_norm": 0.7119743227958679, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2787, "grad_norm": 0.7417448163032532, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2317, "grad_norm": 0.8174124956130981, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2916, "grad_norm": 0.7199270129203796, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2074, "grad_norm": 0.989138662815094, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.75921630859375, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.7844401001930237, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2851, "grad_norm": 0.9127110242843628, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2835, "grad_norm": 0.7972270846366882, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3105, "grad_norm": 0.7458992004394531, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3017, "grad_norm": 0.854924738407135, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2455, "grad_norm": 0.7763816118240356, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}]}
+{"epoch": 4.997150997150997, "step": 877, "epoch_duration": 72.5728759765625, "total_accumulated_duration": 364.45689153671265, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.4021576642990112, "eval_runtime": 2.8786, "eval_samples_per_second": 34.044, "eval_steps_per_second": 4.516, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3666, "grad_norm": 0.7116469144821167, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2579, "grad_norm": 0.6635934114456177, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2688, "grad_norm": 0.7347352504730225, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1805, "grad_norm": 0.693499743938446, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2463, "grad_norm": 0.7138662934303284, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2412, "grad_norm": 0.8807587027549744, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2961, "grad_norm": 0.7191319465637207, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2778, "grad_norm": 0.7447595596313477, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2302, "grad_norm": 0.7865943312644958, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2871, "grad_norm": 0.713374674320221, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2054, "grad_norm": 0.9345150589942932, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.758057713508606, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.78746497631073, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2881, "grad_norm": 0.9097195267677307, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2845, "grad_norm": 0.7972307205200195, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3123, "grad_norm": 0.7442638278007507, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3008, "grad_norm": 0.836273193359375, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2444, "grad_norm": 0.7712854146957397, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3992847204208374, "eval_runtime": 2.8818, "eval_samples_per_second": 34.007, "eval_steps_per_second": 4.511, "epoch": 4.0, "step": 702}, {"loss": 1.1796, "grad_norm": 0.7713205218315125, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1615, "grad_norm": 0.8424011468887329, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2283, "grad_norm": 0.7956175804138184, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1855, "grad_norm": 0.7468942403793335, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1677, "grad_norm": 0.7284650206565857, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.1162, "grad_norm": 0.6964936256408691, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.1868, "grad_norm": 0.8488320708274841, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1688, "grad_norm": 0.796196699142456, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.192, "grad_norm": 0.8746815919876099, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1857, "grad_norm": 0.9144721627235413, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.1836, "grad_norm": 0.7818491458892822, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.204, "grad_norm": 0.7483993768692017, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.191, "grad_norm": 0.7826094627380371, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1254, "grad_norm": 0.7471262216567993, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2276, "grad_norm": 0.8124629259109497, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.1405, "grad_norm": 0.7713154554367065, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1768, "grad_norm": 0.7297055125236511, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}]}
+{"epoch": 6.0, "step": 1053, "epoch_duration": 72.29663968086243, "total_accumulated_duration": 436.7535312175751, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.4021576642990112, "eval_runtime": 2.8786, "eval_samples_per_second": 34.044, "eval_steps_per_second": 4.516, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3666, "grad_norm": 0.7116469144821167, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2579, "grad_norm": 0.6635934114456177, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2688, "grad_norm": 0.7347352504730225, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1805, "grad_norm": 0.693499743938446, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2463, "grad_norm": 0.7138662934303284, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2412, "grad_norm": 0.8807587027549744, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2961, "grad_norm": 0.7191319465637207, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2778, "grad_norm": 0.7447595596313477, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2302, "grad_norm": 0.7865943312644958, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2871, "grad_norm": 0.713374674320221, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2054, "grad_norm": 0.9345150589942932, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.758057713508606, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.78746497631073, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2881, "grad_norm": 0.9097195267677307, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2845, "grad_norm": 0.7972307205200195, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3123, "grad_norm": 0.7442638278007507, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3008, "grad_norm": 0.836273193359375, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2444, "grad_norm": 0.7712854146957397, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3992847204208374, "eval_runtime": 2.8818, "eval_samples_per_second": 34.007, "eval_steps_per_second": 4.511, "epoch": 4.0, "step": 702}, {"loss": 1.1796, "grad_norm": 0.7713205218315125, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1615, "grad_norm": 0.8424011468887329, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2283, "grad_norm": 0.7956175804138184, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1855, "grad_norm": 0.7468942403793335, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1677, "grad_norm": 0.7284650206565857, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.1162, "grad_norm": 0.6964936256408691, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.1868, "grad_norm": 0.8488320708274841, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1688, "grad_norm": 0.796196699142456, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.192, "grad_norm": 0.8746815919876099, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1857, "grad_norm": 0.9144721627235413, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.1836, "grad_norm": 0.7818491458892822, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.204, "grad_norm": 0.7483993768692017, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.191, "grad_norm": 0.7826094627380371, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1254, "grad_norm": 0.7471262216567993, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2276, "grad_norm": 0.8124629259109497, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.1405, "grad_norm": 0.7713154554367065, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1768, "grad_norm": 0.7297055125236511, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4079580307006836, "eval_runtime": 2.8839, "eval_samples_per_second": 33.982, "eval_steps_per_second": 4.508, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.1513, "grad_norm": 0.793989896774292, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.066, "grad_norm": 1.2083884477615356, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.049, "grad_norm": 0.9633278846740723, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.116, "grad_norm": 0.908246636390686, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0497, "grad_norm": 0.9113070964813232, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1089, "grad_norm": 0.8860645294189453, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0345, "grad_norm": 0.8054319024085999, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1365, "grad_norm": 0.9051408171653748, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.1006, "grad_norm": 0.8493460416793823, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1106, "grad_norm": 0.9579766988754272, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0818, "grad_norm": 1.1115326881408691, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1128, "grad_norm": 1.0047303438186646, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1488, "grad_norm": 1.0419378280639648, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0848, "grad_norm": 0.9149153828620911, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0649, "grad_norm": 0.8375725746154785, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1194, "grad_norm": 0.7414003014564514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9575881958007812, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1097, "grad_norm": 0.889681875705719, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}]}
+{"epoch": 4.997150997150997, "step": 877, "epoch_duration": 73.76588153839111, "total_accumulated_duration": 367.9363179206848, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.401209831237793, "eval_runtime": 2.8721, "eval_samples_per_second": 34.121, "eval_steps_per_second": 4.526, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3656, "grad_norm": 0.7109280228614807, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2571, "grad_norm": 0.6746246814727783, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2685, "grad_norm": 0.7202523350715637, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1808, "grad_norm": 0.697090208530426, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2479, "grad_norm": 0.7157464623451233, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2426, "grad_norm": 0.8729232549667358, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2957, "grad_norm": 0.7119743227958679, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2787, "grad_norm": 0.7417448163032532, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2317, "grad_norm": 0.8174124956130981, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2916, "grad_norm": 0.7199270129203796, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2074, "grad_norm": 0.989138662815094, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.75921630859375, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.7844401001930237, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2851, "grad_norm": 0.9127110242843628, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2835, "grad_norm": 0.7972270846366882, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3105, "grad_norm": 0.7458992004394531, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3017, "grad_norm": 0.854924738407135, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2455, "grad_norm": 0.7763816118240356, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3988444805145264, "eval_runtime": 2.8697, "eval_samples_per_second": 34.15, "eval_steps_per_second": 4.53, "epoch": 4.0, "step": 702}, {"loss": 1.178, "grad_norm": 0.877430260181427, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1635, "grad_norm": 0.8365248441696167, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2286, "grad_norm": 0.7748925089836121, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1836, "grad_norm": 0.7695241570472717, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1685, "grad_norm": 0.7229928374290466, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.117, "grad_norm": 0.7035910487174988, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.189, "grad_norm": 0.9075796008110046, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1693, "grad_norm": 0.7957494854927063, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.1945, "grad_norm": 0.8733780384063721, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1867, "grad_norm": 0.8786619901657104, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.185, "grad_norm": 0.7101715803146362, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.2063, "grad_norm": 0.7451328039169312, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.1939, "grad_norm": 0.7830713987350464, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1251, "grad_norm": 0.7804535031318665, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2278, "grad_norm": 0.8121811747550964, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.142, "grad_norm": 0.774864137172699, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1736, "grad_norm": 0.7517814040184021, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}]}
+{"epoch": 6.997150997150997, "step": 1228, "epoch_duration": 72.54125547409058, "total_accumulated_duration": 509.29478669166565, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.4021576642990112, "eval_runtime": 2.8786, "eval_samples_per_second": 34.044, "eval_steps_per_second": 4.516, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3666, "grad_norm": 0.7116469144821167, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2579, "grad_norm": 0.6635934114456177, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2688, "grad_norm": 0.7347352504730225, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1805, "grad_norm": 0.693499743938446, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2463, "grad_norm": 0.7138662934303284, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2412, "grad_norm": 0.8807587027549744, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2961, "grad_norm": 0.7191319465637207, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2778, "grad_norm": 0.7447595596313477, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2302, "grad_norm": 0.7865943312644958, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2871, "grad_norm": 0.713374674320221, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2054, "grad_norm": 0.9345150589942932, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.758057713508606, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.78746497631073, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2881, "grad_norm": 0.9097195267677307, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2845, "grad_norm": 0.7972307205200195, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3123, "grad_norm": 0.7442638278007507, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3008, "grad_norm": 0.836273193359375, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2444, "grad_norm": 0.7712854146957397, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3992847204208374, "eval_runtime": 2.8818, "eval_samples_per_second": 34.007, "eval_steps_per_second": 4.511, "epoch": 4.0, "step": 702}, {"loss": 1.1796, "grad_norm": 0.7713205218315125, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1615, "grad_norm": 0.8424011468887329, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2283, "grad_norm": 0.7956175804138184, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1855, "grad_norm": 0.7468942403793335, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1677, "grad_norm": 0.7284650206565857, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.1162, "grad_norm": 0.6964936256408691, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.1868, "grad_norm": 0.8488320708274841, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1688, "grad_norm": 0.796196699142456, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.192, "grad_norm": 0.8746815919876099, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1857, "grad_norm": 0.9144721627235413, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.1836, "grad_norm": 0.7818491458892822, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.204, "grad_norm": 0.7483993768692017, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.191, "grad_norm": 0.7826094627380371, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1254, "grad_norm": 0.7471262216567993, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2276, "grad_norm": 0.8124629259109497, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.1405, "grad_norm": 0.7713154554367065, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1768, "grad_norm": 0.7297055125236511, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4079580307006836, "eval_runtime": 2.8839, "eval_samples_per_second": 33.982, "eval_steps_per_second": 4.508, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.1513, "grad_norm": 0.793989896774292, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.066, "grad_norm": 1.2083884477615356, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.049, "grad_norm": 0.9633278846740723, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.116, "grad_norm": 0.908246636390686, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0497, "grad_norm": 0.9113070964813232, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1089, "grad_norm": 0.8860645294189453, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0345, "grad_norm": 0.8054319024085999, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1365, "grad_norm": 0.9051408171653748, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.1006, "grad_norm": 0.8493460416793823, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1106, "grad_norm": 0.9579766988754272, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0818, "grad_norm": 1.1115326881408691, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1128, "grad_norm": 1.0047303438186646, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1488, "grad_norm": 1.0419378280639648, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0848, "grad_norm": 0.9149153828620911, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0649, "grad_norm": 0.8375725746154785, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1194, "grad_norm": 0.7414003014564514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9575881958007812, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1097, "grad_norm": 0.889681875705719, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}, {"eval_loss": 1.4382578134536743, "eval_runtime": 2.8787, "eval_samples_per_second": 34.043, "eval_steps_per_second": 4.516, "epoch": 6.0, "step": 1053}, {"loss": 1.0383, "grad_norm": 0.93312007188797, "learning_rate": 0.0002, "epoch": 6.0398860398860394, "step": 1060}, {"loss": 1.038, "grad_norm": 0.9554668068885803, "learning_rate": 0.0002, "epoch": 6.096866096866097, "step": 1070}, {"loss": 0.9846, "grad_norm": 0.8017868995666504, "learning_rate": 0.0002, "epoch": 6.153846153846154, "step": 1080}, {"loss": 0.9767, "grad_norm": 1.1163588762283325, "learning_rate": 0.0002, "epoch": 6.210826210826211, "step": 1090}, {"loss": 1.0239, "grad_norm": 0.9846243262290955, "learning_rate": 0.0002, "epoch": 6.267806267806268, "step": 1100}, {"loss": 0.9773, "grad_norm": 0.930727481842041, "learning_rate": 0.0002, "epoch": 6.3247863247863245, "step": 1110}, {"loss": 0.9885, "grad_norm": 0.9940898418426514, "learning_rate": 0.0002, "epoch": 6.381766381766382, "step": 1120}, {"loss": 1.0289, "grad_norm": 1.0614467859268188, "learning_rate": 0.0002, "epoch": 6.438746438746438, "step": 1130}, {"loss": 1.0301, "grad_norm": 0.9676510095596313, "learning_rate": 0.0002, "epoch": 6.495726495726496, "step": 1140}, {"loss": 0.9773, "grad_norm": 0.8477176427841187, "learning_rate": 0.0002, "epoch": 6.552706552706553, "step": 1150}, {"loss": 0.9944, "grad_norm": 1.0543252229690552, "learning_rate": 0.0002, "epoch": 6.60968660968661, "step": 1160}, {"loss": 0.9939, "grad_norm": 0.9989932775497437, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 1170}, {"loss": 1.0854, "grad_norm": 1.1233140230178833, "learning_rate": 0.0002, "epoch": 6.7236467236467234, "step": 1180}, {"loss": 1.0392, "grad_norm": 1.167738676071167, "learning_rate": 0.0002, "epoch": 6.780626780626781, "step": 1190}, {"loss": 0.9527, "grad_norm": 1.0173308849334717, "learning_rate": 0.0002, "epoch": 6.837606837606837, "step": 1200}, {"loss": 1.0461, "grad_norm": 1.2425651550292969, "learning_rate": 0.0002, "epoch": 6.894586894586895, "step": 1210}, {"loss": 1.0159, "grad_norm": 0.936252772808075, "learning_rate": 0.0002, "epoch": 6.951566951566951, "step": 1220}]}
+{"epoch": 6.0, "step": 1053, "epoch_duration": 73.2647020816803, "total_accumulated_duration": 441.2010200023651, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.401209831237793, "eval_runtime": 2.8721, "eval_samples_per_second": 34.121, "eval_steps_per_second": 4.526, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3656, "grad_norm": 0.7109280228614807, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2571, "grad_norm": 0.6746246814727783, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2685, "grad_norm": 0.7202523350715637, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1808, "grad_norm": 0.697090208530426, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2479, "grad_norm": 0.7157464623451233, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2426, "grad_norm": 0.8729232549667358, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2957, "grad_norm": 0.7119743227958679, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2787, "grad_norm": 0.7417448163032532, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2317, "grad_norm": 0.8174124956130981, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2916, "grad_norm": 0.7199270129203796, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2074, "grad_norm": 0.989138662815094, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.75921630859375, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.7844401001930237, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2851, "grad_norm": 0.9127110242843628, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2835, "grad_norm": 0.7972270846366882, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3105, "grad_norm": 0.7458992004394531, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3017, "grad_norm": 0.854924738407135, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2455, "grad_norm": 0.7763816118240356, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3988444805145264, "eval_runtime": 2.8697, "eval_samples_per_second": 34.15, "eval_steps_per_second": 4.53, "epoch": 4.0, "step": 702}, {"loss": 1.178, "grad_norm": 0.877430260181427, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1635, "grad_norm": 0.8365248441696167, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2286, "grad_norm": 0.7748925089836121, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1836, "grad_norm": 0.7695241570472717, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1685, "grad_norm": 0.7229928374290466, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.117, "grad_norm": 0.7035910487174988, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.189, "grad_norm": 0.9075796008110046, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1693, "grad_norm": 0.7957494854927063, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.1945, "grad_norm": 0.8733780384063721, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1867, "grad_norm": 0.8786619901657104, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.185, "grad_norm": 0.7101715803146362, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.2063, "grad_norm": 0.7451328039169312, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.1939, "grad_norm": 0.7830713987350464, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1251, "grad_norm": 0.7804535031318665, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2278, "grad_norm": 0.8121811747550964, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.142, "grad_norm": 0.774864137172699, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1736, "grad_norm": 0.7517814040184021, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4074795246124268, "eval_runtime": 2.8707, "eval_samples_per_second": 34.138, "eval_steps_per_second": 4.529, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.151, "grad_norm": 0.7974972128868103, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.0637, "grad_norm": 1.1127357482910156, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.0497, "grad_norm": 0.8995195031166077, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.1101, "grad_norm": 0.8325890898704529, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0567, "grad_norm": 0.8830686807632446, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1094, "grad_norm": 0.8856923580169678, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0328, "grad_norm": 0.814587414264679, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1379, "grad_norm": 0.9119254946708679, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.0993, "grad_norm": 0.8547661304473877, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1137, "grad_norm": 0.943742036819458, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0815, "grad_norm": 1.1333340406417847, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1161, "grad_norm": 1.0290982723236084, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1477, "grad_norm": 1.0613716840744019, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0878, "grad_norm": 0.925118088722229, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0658, "grad_norm": 0.828220546245575, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1179, "grad_norm": 0.7466493248939514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9189135432243347, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1114, "grad_norm": 0.9117513298988342, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}]}
+{"epoch": 7.977207977207978, "step": 1400, "epoch_duration": 101.66690945625305, "total_accumulated_duration": 610.9616961479187, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5893, "grad_norm": 1.0233017206192017, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5117, "grad_norm": 4.163138389587402, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1519, "grad_norm": 1.3474042415618896, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.2415039539337158, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.8789, "grad_norm": 1.0774320363998413, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8642, "grad_norm": 0.716522753238678, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7333, "grad_norm": 0.9734901189804077, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.651, "grad_norm": 1.7638314962387085, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5815, "grad_norm": 0.6061757206916809, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6714, "grad_norm": 0.7205694317817688, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.63, "grad_norm": 0.7752107381820679, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6405, "grad_norm": 0.8007442355155945, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.595, "grad_norm": 0.8049221038818359, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6182, "grad_norm": 0.7540143132209778, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6574, "grad_norm": 0.7468489408493042, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4714, "grad_norm": 0.7622578740119934, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5075, "grad_norm": 0.704738438129425, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4978793859481812, "eval_runtime": 2.8823, "eval_samples_per_second": 34.001, "eval_steps_per_second": 4.51, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5307, "grad_norm": 0.6786648035049438, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4725, "grad_norm": 0.6568158268928528, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4754, "grad_norm": 0.7925108671188354, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.543, "grad_norm": 0.6983732581138611, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5132, "grad_norm": 0.6918368935585022, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.3858, "grad_norm": 0.6140615940093994, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4046, "grad_norm": 0.5929235816001892, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4951, "grad_norm": 0.76374751329422, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4439, "grad_norm": 0.6553613543510437, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4252, "grad_norm": 0.9090031385421753, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3674, "grad_norm": 0.6486701369285583, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5102, "grad_norm": 0.8332676291465759, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4243, "grad_norm": 0.6700407266616821, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7524263262748718, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3821, "grad_norm": 0.5268421173095703, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4244, "grad_norm": 0.6470246315002441, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3603, "grad_norm": 0.7546916007995605, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4809, "grad_norm": 0.6527156233787537, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.4244847297668457, "eval_runtime": 2.8825, "eval_samples_per_second": 33.999, "eval_steps_per_second": 4.51, "epoch": 2.0, "step": 351}, {"loss": 1.3558, "grad_norm": 0.8553531765937805, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.3867, "grad_norm": 0.6769258975982666, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3242, "grad_norm": 0.6619579195976257, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.3993, "grad_norm": 0.7349176406860352, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.4022, "grad_norm": 0.6977018117904663, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3072, "grad_norm": 0.7045870423316956, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3586, "grad_norm": 0.7158947587013245, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3159, "grad_norm": 0.6706043481826782, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8902416229248047, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3071, "grad_norm": 0.736464262008667, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.2793, "grad_norm": 0.6882060766220093, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2949, "grad_norm": 0.6580819487571716, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3477, "grad_norm": 0.7671576738357544, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3488, "grad_norm": 0.791325569152832, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3359, "grad_norm": 0.6403379440307617, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.3109, "grad_norm": 0.6506697535514832, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2876, "grad_norm": 0.7321205139160156, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.4021576642990112, "eval_runtime": 2.8786, "eval_samples_per_second": 34.044, "eval_steps_per_second": 4.516, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3666, "grad_norm": 0.7116469144821167, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2579, "grad_norm": 0.6635934114456177, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2688, "grad_norm": 0.7347352504730225, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1805, "grad_norm": 0.693499743938446, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2463, "grad_norm": 0.7138662934303284, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2412, "grad_norm": 0.8807587027549744, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2961, "grad_norm": 0.7191319465637207, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2778, "grad_norm": 0.7447595596313477, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2302, "grad_norm": 0.7865943312644958, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2871, "grad_norm": 0.713374674320221, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2054, "grad_norm": 0.9345150589942932, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.758057713508606, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.78746497631073, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2881, "grad_norm": 0.9097195267677307, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2845, "grad_norm": 0.7972307205200195, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3123, "grad_norm": 0.7442638278007507, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3008, "grad_norm": 0.836273193359375, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2444, "grad_norm": 0.7712854146957397, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3992847204208374, "eval_runtime": 2.8818, "eval_samples_per_second": 34.007, "eval_steps_per_second": 4.511, "epoch": 4.0, "step": 702}, {"loss": 1.1796, "grad_norm": 0.7713205218315125, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1615, "grad_norm": 0.8424011468887329, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2283, "grad_norm": 0.7956175804138184, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1855, "grad_norm": 0.7468942403793335, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1677, "grad_norm": 0.7284650206565857, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.1162, "grad_norm": 0.6964936256408691, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.1868, "grad_norm": 0.8488320708274841, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1688, "grad_norm": 0.796196699142456, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.192, "grad_norm": 0.8746815919876099, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1857, "grad_norm": 0.9144721627235413, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.1836, "grad_norm": 0.7818491458892822, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.204, "grad_norm": 0.7483993768692017, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.191, "grad_norm": 0.7826094627380371, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1254, "grad_norm": 0.7471262216567993, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2276, "grad_norm": 0.8124629259109497, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.1405, "grad_norm": 0.7713154554367065, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1768, "grad_norm": 0.7297055125236511, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4079580307006836, "eval_runtime": 2.8839, "eval_samples_per_second": 33.982, "eval_steps_per_second": 4.508, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.1513, "grad_norm": 0.793989896774292, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.066, "grad_norm": 1.2083884477615356, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.049, "grad_norm": 0.9633278846740723, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.116, "grad_norm": 0.908246636390686, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0497, "grad_norm": 0.9113070964813232, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1089, "grad_norm": 0.8860645294189453, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0345, "grad_norm": 0.8054319024085999, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1365, "grad_norm": 0.9051408171653748, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.1006, "grad_norm": 0.8493460416793823, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1106, "grad_norm": 0.9579766988754272, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0818, "grad_norm": 1.1115326881408691, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1128, "grad_norm": 1.0047303438186646, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1488, "grad_norm": 1.0419378280639648, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0848, "grad_norm": 0.9149153828620911, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0649, "grad_norm": 0.8375725746154785, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1194, "grad_norm": 0.7414003014564514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9575881958007812, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1097, "grad_norm": 0.889681875705719, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}, {"eval_loss": 1.4382578134536743, "eval_runtime": 2.8787, "eval_samples_per_second": 34.043, "eval_steps_per_second": 4.516, "epoch": 6.0, "step": 1053}, {"loss": 1.0383, "grad_norm": 0.93312007188797, "learning_rate": 0.0002, "epoch": 6.0398860398860394, "step": 1060}, {"loss": 1.038, "grad_norm": 0.9554668068885803, "learning_rate": 0.0002, "epoch": 6.096866096866097, "step": 1070}, {"loss": 0.9846, "grad_norm": 0.8017868995666504, "learning_rate": 0.0002, "epoch": 6.153846153846154, "step": 1080}, {"loss": 0.9767, "grad_norm": 1.1163588762283325, "learning_rate": 0.0002, "epoch": 6.210826210826211, "step": 1090}, {"loss": 1.0239, "grad_norm": 0.9846243262290955, "learning_rate": 0.0002, "epoch": 6.267806267806268, "step": 1100}, {"loss": 0.9773, "grad_norm": 0.930727481842041, "learning_rate": 0.0002, "epoch": 6.3247863247863245, "step": 1110}, {"loss": 0.9885, "grad_norm": 0.9940898418426514, "learning_rate": 0.0002, "epoch": 6.381766381766382, "step": 1120}, {"loss": 1.0289, "grad_norm": 1.0614467859268188, "learning_rate": 0.0002, "epoch": 6.438746438746438, "step": 1130}, {"loss": 1.0301, "grad_norm": 0.9676510095596313, "learning_rate": 0.0002, "epoch": 6.495726495726496, "step": 1140}, {"loss": 0.9773, "grad_norm": 0.8477176427841187, "learning_rate": 0.0002, "epoch": 6.552706552706553, "step": 1150}, {"loss": 0.9944, "grad_norm": 1.0543252229690552, "learning_rate": 0.0002, "epoch": 6.60968660968661, "step": 1160}, {"loss": 0.9939, "grad_norm": 0.9989932775497437, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 1170}, {"loss": 1.0854, "grad_norm": 1.1233140230178833, "learning_rate": 0.0002, "epoch": 6.7236467236467234, "step": 1180}, {"loss": 1.0392, "grad_norm": 1.167738676071167, "learning_rate": 0.0002, "epoch": 6.780626780626781, "step": 1190}, {"loss": 0.9527, "grad_norm": 1.0173308849334717, "learning_rate": 0.0002, "epoch": 6.837606837606837, "step": 1200}, {"loss": 1.0461, "grad_norm": 1.2425651550292969, "learning_rate": 0.0002, "epoch": 6.894586894586895, "step": 1210}, {"loss": 1.0159, "grad_norm": 0.936252772808075, "learning_rate": 0.0002, "epoch": 6.951566951566951, "step": 1220}, {"eval_loss": 1.4745711088180542, "eval_runtime": 2.8963, "eval_samples_per_second": 33.836, "eval_steps_per_second": 4.488, "epoch": 6.997150997150997, "step": 1228}, {"loss": 1.0114, "grad_norm": 0.964927613735199, "learning_rate": 0.0002, "epoch": 7.0085470085470085, "step": 1230}, {"loss": 0.9128, "grad_norm": 1.0938352346420288, "learning_rate": 0.0002, "epoch": 7.065527065527066, "step": 1240}, {"loss": 0.9237, "grad_norm": 0.9703038930892944, "learning_rate": 0.0002, "epoch": 7.122507122507122, "step": 1250}, {"loss": 0.9082, "grad_norm": 1.2634679079055786, "learning_rate": 0.0002, "epoch": 7.17948717948718, "step": 1260}, {"loss": 0.9337, "grad_norm": 1.0933488607406616, "learning_rate": 0.0002, "epoch": 7.236467236467236, "step": 1270}, {"loss": 0.896, "grad_norm": 1.1065915822982788, "learning_rate": 0.0002, "epoch": 7.293447293447294, "step": 1280}, {"loss": 0.9334, "grad_norm": 1.2566848993301392, "learning_rate": 0.0002, "epoch": 7.35042735042735, "step": 1290}, {"loss": 0.8398, "grad_norm": 1.0640543699264526, "learning_rate": 0.0002, "epoch": 7.407407407407407, "step": 1300}, {"loss": 0.9353, "grad_norm": 1.1277321577072144, "learning_rate": 0.0002, "epoch": 7.464387464387464, "step": 1310}, {"loss": 0.9089, "grad_norm": 1.023599624633789, "learning_rate": 0.0002, "epoch": 7.521367521367521, "step": 1320}, {"loss": 0.946, "grad_norm": 1.1464563608169556, "learning_rate": 0.0002, "epoch": 7.578347578347579, "step": 1330}, {"loss": 0.9418, "grad_norm": 1.1366990804672241, "learning_rate": 0.0002, "epoch": 7.635327635327635, "step": 1340}, {"loss": 0.9043, "grad_norm": 0.8951204419136047, "learning_rate": 0.0002, "epoch": 7.6923076923076925, "step": 1350}, {"loss": 0.9075, "grad_norm": 1.1149132251739502, "learning_rate": 0.0002, "epoch": 7.749287749287749, "step": 1360}, {"loss": 0.9693, "grad_norm": 1.2248684167861938, "learning_rate": 0.0002, "epoch": 7.806267806267806, "step": 1370}, {"loss": 0.9242, "grad_norm": 1.0078679323196411, "learning_rate": 0.0002, "epoch": 7.863247863247864, "step": 1380}, {"loss": 0.972, "grad_norm": 1.0135971307754517, "learning_rate": 0.0002, "epoch": 7.92022792022792, "step": 1390}, {"loss": 0.9393, "grad_norm": 1.2399200201034546, "learning_rate": 0.0002, "epoch": 7.977207977207978, "step": 1400}]}
+{"epoch": 6.997150997150997, "step": 1228, "epoch_duration": 103.41745567321777, "total_accumulated_duration": 544.6184756755829, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3048.73388671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.401209831237793, "eval_runtime": 2.8721, "eval_samples_per_second": 34.121, "eval_steps_per_second": 4.526, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3656, "grad_norm": 0.7109280228614807, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2571, "grad_norm": 0.6746246814727783, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2685, "grad_norm": 0.7202523350715637, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1808, "grad_norm": 0.697090208530426, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2479, "grad_norm": 0.7157464623451233, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2426, "grad_norm": 0.8729232549667358, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2957, "grad_norm": 0.7119743227958679, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2787, "grad_norm": 0.7417448163032532, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2317, "grad_norm": 0.8174124956130981, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2916, "grad_norm": 0.7199270129203796, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2074, "grad_norm": 0.989138662815094, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.75921630859375, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.7844401001930237, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2851, "grad_norm": 0.9127110242843628, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2835, "grad_norm": 0.7972270846366882, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3105, "grad_norm": 0.7458992004394531, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3017, "grad_norm": 0.854924738407135, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2455, "grad_norm": 0.7763816118240356, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3988444805145264, "eval_runtime": 2.8697, "eval_samples_per_second": 34.15, "eval_steps_per_second": 4.53, "epoch": 4.0, "step": 702}, {"loss": 1.178, "grad_norm": 0.877430260181427, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1635, "grad_norm": 0.8365248441696167, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2286, "grad_norm": 0.7748925089836121, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1836, "grad_norm": 0.7695241570472717, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1685, "grad_norm": 0.7229928374290466, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.117, "grad_norm": 0.7035910487174988, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.189, "grad_norm": 0.9075796008110046, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1693, "grad_norm": 0.7957494854927063, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.1945, "grad_norm": 0.8733780384063721, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1867, "grad_norm": 0.8786619901657104, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.185, "grad_norm": 0.7101715803146362, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.2063, "grad_norm": 0.7451328039169312, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.1939, "grad_norm": 0.7830713987350464, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1251, "grad_norm": 0.7804535031318665, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2278, "grad_norm": 0.8121811747550964, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.142, "grad_norm": 0.774864137172699, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1736, "grad_norm": 0.7517814040184021, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4074795246124268, "eval_runtime": 2.8707, "eval_samples_per_second": 34.138, "eval_steps_per_second": 4.529, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.151, "grad_norm": 0.7974972128868103, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.0637, "grad_norm": 1.1127357482910156, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.0497, "grad_norm": 0.8995195031166077, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.1101, "grad_norm": 0.8325890898704529, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0567, "grad_norm": 0.8830686807632446, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1094, "grad_norm": 0.8856923580169678, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0328, "grad_norm": 0.814587414264679, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1379, "grad_norm": 0.9119254946708679, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.0993, "grad_norm": 0.8547661304473877, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1137, "grad_norm": 0.943742036819458, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0815, "grad_norm": 1.1333340406417847, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1161, "grad_norm": 1.0290982723236084, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1477, "grad_norm": 1.0613716840744019, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0878, "grad_norm": 0.925118088722229, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0658, "grad_norm": 0.828220546245575, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1179, "grad_norm": 0.7466493248939514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9189135432243347, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1114, "grad_norm": 0.9117513298988342, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}, {"eval_loss": 1.4333235025405884, "eval_runtime": 2.9267, "eval_samples_per_second": 33.485, "eval_steps_per_second": 4.442, "epoch": 6.0, "step": 1053}, {"loss": 1.0368, "grad_norm": 0.9506599307060242, "learning_rate": 0.0002, "epoch": 6.0398860398860394, "step": 1060}, {"loss": 1.0376, "grad_norm": 0.9809837937355042, "learning_rate": 0.0002, "epoch": 6.096866096866097, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.852557361125946, "learning_rate": 0.0002, "epoch": 6.153846153846154, "step": 1080}, {"loss": 0.9782, "grad_norm": 1.135279893875122, "learning_rate": 0.0002, "epoch": 6.210826210826211, "step": 1090}, {"loss": 1.0238, "grad_norm": 1.0243879556655884, "learning_rate": 0.0002, "epoch": 6.267806267806268, "step": 1100}, {"loss": 0.9815, "grad_norm": 0.9213914275169373, "learning_rate": 0.0002, "epoch": 6.3247863247863245, "step": 1110}, {"loss": 0.9899, "grad_norm": 1.0042028427124023, "learning_rate": 0.0002, "epoch": 6.381766381766382, "step": 1120}, {"loss": 1.0249, "grad_norm": 1.1024253368377686, "learning_rate": 0.0002, "epoch": 6.438746438746438, "step": 1130}, {"loss": 1.0305, "grad_norm": 0.9245727062225342, "learning_rate": 0.0002, "epoch": 6.495726495726496, "step": 1140}, {"loss": 0.9766, "grad_norm": 0.8309272527694702, "learning_rate": 0.0002, "epoch": 6.552706552706553, "step": 1150}, {"loss": 0.9945, "grad_norm": 1.029746651649475, "learning_rate": 0.0002, "epoch": 6.60968660968661, "step": 1160}, {"loss": 0.9955, "grad_norm": 0.9932991862297058, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 1170}, {"loss": 1.0808, "grad_norm": 1.1597973108291626, "learning_rate": 0.0002, "epoch": 6.7236467236467234, "step": 1180}, {"loss": 1.0407, "grad_norm": 1.1373951435089111, "learning_rate": 0.0002, "epoch": 6.780626780626781, "step": 1190}, {"loss": 0.9513, "grad_norm": 1.0308297872543335, "learning_rate": 0.0002, "epoch": 6.837606837606837, "step": 1200}, {"loss": 1.0437, "grad_norm": 1.1555122137069702, "learning_rate": 0.0002, "epoch": 6.894586894586895, "step": 1210}, {"loss": 1.0164, "grad_norm": 0.9829897284507751, "learning_rate": 0.0002, "epoch": 6.951566951566951, "step": 1220}]}
+{"epoch": 7.977207977207978, "step": 1400, "epoch_duration": 74.71395587921143, "total_accumulated_duration": 619.3324315547943, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15079.29833984375}, "avg_memory_reserved": {"GPU_0": 20172.0}, "peak_memory_reserved": {"GPU_0": 20172.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-2790-sd-10000/checkpoint-702", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.5896, "grad_norm": 1.0227872133255005, "learning_rate": 0.0002, "epoch": 0.05698005698005698, "step": 10}, {"loss": 2.5124, "grad_norm": 3.86788010597229, "learning_rate": 0.0002, "epoch": 0.11396011396011396, "step": 20}, {"loss": 2.1576, "grad_norm": 1.3474394083023071, "learning_rate": 0.0002, "epoch": 0.17094017094017094, "step": 30}, {"loss": 2.0115, "grad_norm": 1.1816296577453613, "learning_rate": 0.0002, "epoch": 0.22792022792022792, "step": 40}, {"loss": 1.875, "grad_norm": 1.0907047986984253, "learning_rate": 0.0002, "epoch": 0.2849002849002849, "step": 50}, {"loss": 1.8608, "grad_norm": 0.9163471460342407, "learning_rate": 0.0002, "epoch": 0.3418803418803419, "step": 60}, {"loss": 1.7334, "grad_norm": 1.0441275835037231, "learning_rate": 0.0002, "epoch": 0.39886039886039887, "step": 70}, {"loss": 1.6496, "grad_norm": 1.0836364030838013, "learning_rate": 0.0002, "epoch": 0.45584045584045585, "step": 80}, {"loss": 1.5814, "grad_norm": 0.5817112922668457, "learning_rate": 0.0002, "epoch": 0.5128205128205128, "step": 90}, {"loss": 1.6697, "grad_norm": 0.8991169929504395, "learning_rate": 0.0002, "epoch": 0.5698005698005698, "step": 100}, {"loss": 1.621, "grad_norm": 1.1820793151855469, "learning_rate": 0.0002, "epoch": 0.6267806267806267, "step": 110}, {"loss": 1.6376, "grad_norm": 0.8205533623695374, "learning_rate": 0.0002, "epoch": 0.6837606837606838, "step": 120}, {"loss": 1.5902, "grad_norm": 0.8154979348182678, "learning_rate": 0.0002, "epoch": 0.7407407407407407, "step": 130}, {"loss": 1.6139, "grad_norm": 0.7292681336402893, "learning_rate": 0.0002, "epoch": 0.7977207977207977, "step": 140}, {"loss": 1.6554, "grad_norm": 0.7737869024276733, "learning_rate": 0.0002, "epoch": 0.8547008547008547, "step": 150}, {"loss": 1.4696, "grad_norm": 0.7786843180656433, "learning_rate": 0.0002, "epoch": 0.9116809116809117, "step": 160}, {"loss": 1.5062, "grad_norm": 0.6918405294418335, "learning_rate": 0.0002, "epoch": 0.9686609686609686, "step": 170}, {"eval_loss": 1.4962449073791504, "eval_runtime": 2.869, "eval_samples_per_second": 34.158, "eval_steps_per_second": 4.531, "epoch": 0.9971509971509972, "step": 175}, {"loss": 1.5305, "grad_norm": 0.6754891872406006, "learning_rate": 0.0002, "epoch": 1.0256410256410255, "step": 180}, {"loss": 1.4709, "grad_norm": 0.6875350475311279, "learning_rate": 0.0002, "epoch": 1.0826210826210827, "step": 190}, {"loss": 1.4744, "grad_norm": 0.7870411276817322, "learning_rate": 0.0002, "epoch": 1.1396011396011396, "step": 200}, {"loss": 1.5414, "grad_norm": 0.6934282779693604, "learning_rate": 0.0002, "epoch": 1.1965811965811965, "step": 210}, {"loss": 1.5129, "grad_norm": 0.6980162858963013, "learning_rate": 0.0002, "epoch": 1.2535612535612537, "step": 220}, {"loss": 1.385, "grad_norm": 0.6163203120231628, "learning_rate": 0.0002, "epoch": 1.3105413105413106, "step": 230}, {"loss": 1.4028, "grad_norm": 0.5967347025871277, "learning_rate": 0.0002, "epoch": 1.3675213675213675, "step": 240}, {"loss": 1.4945, "grad_norm": 0.7622564435005188, "learning_rate": 0.0002, "epoch": 1.4245014245014245, "step": 250}, {"loss": 1.4426, "grad_norm": 0.6667674779891968, "learning_rate": 0.0002, "epoch": 1.4814814814814814, "step": 260}, {"loss": 1.4227, "grad_norm": 0.9225417971611023, "learning_rate": 0.0002, "epoch": 1.5384615384615383, "step": 270}, {"loss": 1.3687, "grad_norm": 0.6473053097724915, "learning_rate": 0.0002, "epoch": 1.5954415954415955, "step": 280}, {"loss": 1.5086, "grad_norm": 0.8250042796134949, "learning_rate": 0.0002, "epoch": 1.6524216524216524, "step": 290}, {"loss": 1.4259, "grad_norm": 0.6660609841346741, "learning_rate": 0.0002, "epoch": 1.7094017094017095, "step": 300}, {"loss": 1.373, "grad_norm": 0.7542873620986938, "learning_rate": 0.0002, "epoch": 1.7663817663817665, "step": 310}, {"loss": 1.3823, "grad_norm": 0.5261648297309875, "learning_rate": 0.0002, "epoch": 1.8233618233618234, "step": 320}, {"loss": 1.4251, "grad_norm": 0.6519118547439575, "learning_rate": 0.0002, "epoch": 1.8803418803418803, "step": 330}, {"loss": 1.3613, "grad_norm": 0.7584664821624756, "learning_rate": 0.0002, "epoch": 1.9373219373219372, "step": 340}, {"loss": 1.4797, "grad_norm": 0.6466017365455627, "learning_rate": 0.0002, "epoch": 1.9943019943019942, "step": 350}, {"eval_loss": 1.424173355102539, "eval_runtime": 2.8659, "eval_samples_per_second": 34.195, "eval_steps_per_second": 4.536, "epoch": 2.0, "step": 351}, {"loss": 1.3555, "grad_norm": 0.7457601428031921, "learning_rate": 0.0002, "epoch": 2.051282051282051, "step": 360}, {"loss": 1.387, "grad_norm": 0.6645848751068115, "learning_rate": 0.0002, "epoch": 2.1082621082621085, "step": 370}, {"loss": 1.3244, "grad_norm": 0.6545299887657166, "learning_rate": 0.0002, "epoch": 2.1652421652421654, "step": 380}, {"loss": 1.4025, "grad_norm": 0.7429937124252319, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 390}, {"loss": 1.3995, "grad_norm": 0.6929682493209839, "learning_rate": 0.0002, "epoch": 2.2792022792022792, "step": 400}, {"loss": 1.3073, "grad_norm": 0.6999889016151428, "learning_rate": 0.0002, "epoch": 2.336182336182336, "step": 410}, {"loss": 1.3573, "grad_norm": 0.7174718379974365, "learning_rate": 0.0002, "epoch": 2.393162393162393, "step": 420}, {"loss": 1.3169, "grad_norm": 0.667317807674408, "learning_rate": 0.0002, "epoch": 2.45014245014245, "step": 430}, {"loss": 1.3877, "grad_norm": 0.8981409072875977, "learning_rate": 0.0002, "epoch": 2.5071225071225074, "step": 440}, {"loss": 1.3085, "grad_norm": 0.7560263872146606, "learning_rate": 0.0002, "epoch": 2.564102564102564, "step": 450}, {"loss": 1.278, "grad_norm": 0.699364185333252, "learning_rate": 0.0002, "epoch": 2.6210826210826212, "step": 460}, {"loss": 1.2962, "grad_norm": 0.666292667388916, "learning_rate": 0.0002, "epoch": 2.678062678062678, "step": 470}, {"loss": 1.3471, "grad_norm": 0.7564692497253418, "learning_rate": 0.0002, "epoch": 2.735042735042735, "step": 480}, {"loss": 1.3489, "grad_norm": 0.7561964392662048, "learning_rate": 0.0002, "epoch": 2.792022792022792, "step": 490}, {"loss": 1.3357, "grad_norm": 0.6506860852241516, "learning_rate": 0.0002, "epoch": 2.849002849002849, "step": 500}, {"loss": 1.311, "grad_norm": 0.6425383687019348, "learning_rate": 0.0002, "epoch": 2.905982905982906, "step": 510}, {"loss": 1.2879, "grad_norm": 0.7424822449684143, "learning_rate": 0.0002, "epoch": 2.962962962962963, "step": 520}, {"eval_loss": 1.401209831237793, "eval_runtime": 2.8721, "eval_samples_per_second": 34.121, "eval_steps_per_second": 4.526, "epoch": 2.9971509971509973, "step": 526}, {"loss": 1.3656, "grad_norm": 0.7109280228614807, "learning_rate": 0.0002, "epoch": 3.0199430199430197, "step": 530}, {"loss": 1.2571, "grad_norm": 0.6746246814727783, "learning_rate": 0.0002, "epoch": 3.076923076923077, "step": 540}, {"loss": 1.2685, "grad_norm": 0.7202523350715637, "learning_rate": 0.0002, "epoch": 3.133903133903134, "step": 550}, {"loss": 1.1808, "grad_norm": 0.697090208530426, "learning_rate": 0.0002, "epoch": 3.190883190883191, "step": 560}, {"loss": 1.2479, "grad_norm": 0.7157464623451233, "learning_rate": 0.0002, "epoch": 3.247863247863248, "step": 570}, {"loss": 1.2426, "grad_norm": 0.8729232549667358, "learning_rate": 0.0002, "epoch": 3.304843304843305, "step": 580}, {"loss": 1.2957, "grad_norm": 0.7119743227958679, "learning_rate": 0.0002, "epoch": 3.3618233618233617, "step": 590}, {"loss": 1.2787, "grad_norm": 0.7417448163032532, "learning_rate": 0.0002, "epoch": 3.4188034188034186, "step": 600}, {"loss": 1.2317, "grad_norm": 0.8174124956130981, "learning_rate": 0.0002, "epoch": 3.4757834757834756, "step": 610}, {"loss": 1.2916, "grad_norm": 0.7199270129203796, "learning_rate": 0.0002, "epoch": 3.532763532763533, "step": 620}, {"loss": 1.2074, "grad_norm": 0.989138662815094, "learning_rate": 0.0002, "epoch": 3.58974358974359, "step": 630}, {"loss": 1.2263, "grad_norm": 0.75921630859375, "learning_rate": 0.0002, "epoch": 3.646723646723647, "step": 640}, {"loss": 1.2319, "grad_norm": 0.7844401001930237, "learning_rate": 0.0002, "epoch": 3.7037037037037037, "step": 650}, {"loss": 1.2851, "grad_norm": 0.9127110242843628, "learning_rate": 0.0002, "epoch": 3.7606837606837606, "step": 660}, {"loss": 1.2835, "grad_norm": 0.7972270846366882, "learning_rate": 0.0002, "epoch": 3.8176638176638176, "step": 670}, {"loss": 1.3105, "grad_norm": 0.7458992004394531, "learning_rate": 0.0002, "epoch": 3.8746438746438745, "step": 680}, {"loss": 1.3017, "grad_norm": 0.854924738407135, "learning_rate": 0.0002, "epoch": 3.931623931623932, "step": 690}, {"loss": 1.2455, "grad_norm": 0.7763816118240356, "learning_rate": 0.0002, "epoch": 3.9886039886039883, "step": 700}, {"eval_loss": 1.3988444805145264, "eval_runtime": 2.8697, "eval_samples_per_second": 34.15, "eval_steps_per_second": 4.53, "epoch": 4.0, "step": 702}, {"loss": 1.178, "grad_norm": 0.877430260181427, "learning_rate": 0.0002, "epoch": 4.045584045584046, "step": 710}, {"loss": 1.1635, "grad_norm": 0.8365248441696167, "learning_rate": 0.0002, "epoch": 4.102564102564102, "step": 720}, {"loss": 1.2286, "grad_norm": 0.7748925089836121, "learning_rate": 0.0002, "epoch": 4.15954415954416, "step": 730}, {"loss": 1.1836, "grad_norm": 0.7695241570472717, "learning_rate": 0.0002, "epoch": 4.216524216524217, "step": 740}, {"loss": 1.1685, "grad_norm": 0.7229928374290466, "learning_rate": 0.0002, "epoch": 4.273504273504273, "step": 750}, {"loss": 1.117, "grad_norm": 0.7035910487174988, "learning_rate": 0.0002, "epoch": 4.330484330484331, "step": 760}, {"loss": 1.189, "grad_norm": 0.9075796008110046, "learning_rate": 0.0002, "epoch": 4.387464387464387, "step": 770}, {"loss": 1.1693, "grad_norm": 0.7957494854927063, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 780}, {"loss": 1.1945, "grad_norm": 0.8733780384063721, "learning_rate": 0.0002, "epoch": 4.501424501424501, "step": 790}, {"loss": 1.1867, "grad_norm": 0.8786619901657104, "learning_rate": 0.0002, "epoch": 4.5584045584045585, "step": 800}, {"loss": 1.185, "grad_norm": 0.7101715803146362, "learning_rate": 0.0002, "epoch": 4.615384615384615, "step": 810}, {"loss": 1.2063, "grad_norm": 0.7451328039169312, "learning_rate": 0.0002, "epoch": 4.672364672364672, "step": 820}, {"loss": 1.1939, "grad_norm": 0.7830713987350464, "learning_rate": 0.0002, "epoch": 4.72934472934473, "step": 830}, {"loss": 1.1251, "grad_norm": 0.7804535031318665, "learning_rate": 0.0002, "epoch": 4.786324786324786, "step": 840}, {"loss": 1.2278, "grad_norm": 0.8121811747550964, "learning_rate": 0.0002, "epoch": 4.843304843304844, "step": 850}, {"loss": 1.142, "grad_norm": 0.774864137172699, "learning_rate": 0.0002, "epoch": 4.9002849002849, "step": 860}, {"loss": 1.1736, "grad_norm": 0.7517814040184021, "learning_rate": 0.0002, "epoch": 4.957264957264957, "step": 870}, {"eval_loss": 1.4074795246124268, "eval_runtime": 2.8707, "eval_samples_per_second": 34.138, "eval_steps_per_second": 4.529, "epoch": 4.997150997150997, "step": 877}, {"loss": 1.151, "grad_norm": 0.7974972128868103, "learning_rate": 0.0002, "epoch": 5.014245014245014, "step": 880}, {"loss": 1.0637, "grad_norm": 1.1127357482910156, "learning_rate": 0.0002, "epoch": 5.071225071225071, "step": 890}, {"loss": 1.0497, "grad_norm": 0.8995195031166077, "learning_rate": 0.0002, "epoch": 5.128205128205128, "step": 900}, {"loss": 1.1101, "grad_norm": 0.8325890898704529, "learning_rate": 0.0002, "epoch": 5.185185185185185, "step": 910}, {"loss": 1.0567, "grad_norm": 0.8830686807632446, "learning_rate": 0.0002, "epoch": 5.2421652421652425, "step": 920}, {"loss": 1.1094, "grad_norm": 0.8856923580169678, "learning_rate": 0.0002, "epoch": 5.299145299145299, "step": 930}, {"loss": 1.0328, "grad_norm": 0.814587414264679, "learning_rate": 0.0002, "epoch": 5.356125356125356, "step": 940}, {"loss": 1.1379, "grad_norm": 0.9119254946708679, "learning_rate": 0.0002, "epoch": 5.413105413105413, "step": 950}, {"loss": 1.0993, "grad_norm": 0.8547661304473877, "learning_rate": 0.0002, "epoch": 5.47008547008547, "step": 960}, {"loss": 1.1137, "grad_norm": 0.943742036819458, "learning_rate": 0.0002, "epoch": 5.527065527065528, "step": 970}, {"loss": 1.0815, "grad_norm": 1.1333340406417847, "learning_rate": 0.0002, "epoch": 5.584045584045584, "step": 980}, {"loss": 1.1161, "grad_norm": 1.0290982723236084, "learning_rate": 0.0002, "epoch": 5.641025641025641, "step": 990}, {"loss": 1.1477, "grad_norm": 1.0613716840744019, "learning_rate": 0.0002, "epoch": 5.698005698005698, "step": 1000}, {"loss": 1.0878, "grad_norm": 0.925118088722229, "learning_rate": 0.0002, "epoch": 5.754985754985755, "step": 1010}, {"loss": 1.0658, "grad_norm": 0.828220546245575, "learning_rate": 0.0002, "epoch": 5.811965811965812, "step": 1020}, {"loss": 1.1179, "grad_norm": 0.7466493248939514, "learning_rate": 0.0002, "epoch": 5.868945868945869, "step": 1030}, {"loss": 1.1064, "grad_norm": 0.9189135432243347, "learning_rate": 0.0002, "epoch": 5.925925925925926, "step": 1040}, {"loss": 1.1114, "grad_norm": 0.9117513298988342, "learning_rate": 0.0002, "epoch": 5.982905982905983, "step": 1050}, {"eval_loss": 1.4333235025405884, "eval_runtime": 2.9267, "eval_samples_per_second": 33.485, "eval_steps_per_second": 4.442, "epoch": 6.0, "step": 1053}, {"loss": 1.0368, "grad_norm": 0.9506599307060242, "learning_rate": 0.0002, "epoch": 6.0398860398860394, "step": 1060}, {"loss": 1.0376, "grad_norm": 0.9809837937355042, "learning_rate": 0.0002, "epoch": 6.096866096866097, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.852557361125946, "learning_rate": 0.0002, "epoch": 6.153846153846154, "step": 1080}, {"loss": 0.9782, "grad_norm": 1.135279893875122, "learning_rate": 0.0002, "epoch": 6.210826210826211, "step": 1090}, {"loss": 1.0238, "grad_norm": 1.0243879556655884, "learning_rate": 0.0002, "epoch": 6.267806267806268, "step": 1100}, {"loss": 0.9815, "grad_norm": 0.9213914275169373, "learning_rate": 0.0002, "epoch": 6.3247863247863245, "step": 1110}, {"loss": 0.9899, "grad_norm": 1.0042028427124023, "learning_rate": 0.0002, "epoch": 6.381766381766382, "step": 1120}, {"loss": 1.0249, "grad_norm": 1.1024253368377686, "learning_rate": 0.0002, "epoch": 6.438746438746438, "step": 1130}, {"loss": 1.0305, "grad_norm": 0.9245727062225342, "learning_rate": 0.0002, "epoch": 6.495726495726496, "step": 1140}, {"loss": 0.9766, "grad_norm": 0.8309272527694702, "learning_rate": 0.0002, "epoch": 6.552706552706553, "step": 1150}, {"loss": 0.9945, "grad_norm": 1.029746651649475, "learning_rate": 0.0002, "epoch": 6.60968660968661, "step": 1160}, {"loss": 0.9955, "grad_norm": 0.9932991862297058, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 1170}, {"loss": 1.0808, "grad_norm": 1.1597973108291626, "learning_rate": 0.0002, "epoch": 6.7236467236467234, "step": 1180}, {"loss": 1.0407, "grad_norm": 1.1373951435089111, "learning_rate": 0.0002, "epoch": 6.780626780626781, "step": 1190}, {"loss": 0.9513, "grad_norm": 1.0308297872543335, "learning_rate": 0.0002, "epoch": 6.837606837606837, "step": 1200}, {"loss": 1.0437, "grad_norm": 1.1555122137069702, "learning_rate": 0.0002, "epoch": 6.894586894586895, "step": 1210}, {"loss": 1.0164, "grad_norm": 0.9829897284507751, "learning_rate": 0.0002, "epoch": 6.951566951566951, "step": 1220}, {"eval_loss": 1.4769021272659302, "eval_runtime": 2.8681, "eval_samples_per_second": 34.168, "eval_steps_per_second": 4.533, "epoch": 6.997150997150997, "step": 1228}, {"loss": 1.0111, "grad_norm": 1.1083747148513794, "learning_rate": 0.0002, "epoch": 7.0085470085470085, "step": 1230}, {"loss": 0.9179, "grad_norm": 1.1454236507415771, "learning_rate": 0.0002, "epoch": 7.065527065527066, "step": 1240}, {"loss": 0.9271, "grad_norm": 0.9501869082450867, "learning_rate": 0.0002, "epoch": 7.122507122507122, "step": 1250}, {"loss": 0.9121, "grad_norm": 1.2393906116485596, "learning_rate": 0.0002, "epoch": 7.17948717948718, "step": 1260}, {"loss": 0.9396, "grad_norm": 1.0671173334121704, "learning_rate": 0.0002, "epoch": 7.236467236467236, "step": 1270}, {"loss": 0.9023, "grad_norm": 1.1026686429977417, "learning_rate": 0.0002, "epoch": 7.293447293447294, "step": 1280}, {"loss": 0.9267, "grad_norm": 1.2422044277191162, "learning_rate": 0.0002, "epoch": 7.35042735042735, "step": 1290}, {"loss": 0.8394, "grad_norm": 1.0772203207015991, "learning_rate": 0.0002, "epoch": 7.407407407407407, "step": 1300}, {"loss": 0.9361, "grad_norm": 1.1025265455245972, "learning_rate": 0.0002, "epoch": 7.464387464387464, "step": 1310}, {"loss": 0.9124, "grad_norm": 1.0232294797897339, "learning_rate": 0.0002, "epoch": 7.521367521367521, "step": 1320}, {"loss": 0.9412, "grad_norm": 1.2126119136810303, "learning_rate": 0.0002, "epoch": 7.578347578347579, "step": 1330}, {"loss": 0.9405, "grad_norm": 1.2359609603881836, "learning_rate": 0.0002, "epoch": 7.635327635327635, "step": 1340}, {"loss": 0.9096, "grad_norm": 0.9109336733818054, "learning_rate": 0.0002, "epoch": 7.6923076923076925, "step": 1350}, {"loss": 0.9038, "grad_norm": 1.0734586715698242, "learning_rate": 0.0002, "epoch": 7.749287749287749, "step": 1360}, {"loss": 0.9674, "grad_norm": 1.1725562810897827, "learning_rate": 0.0002, "epoch": 7.806267806267806, "step": 1370}, {"loss": 0.9211, "grad_norm": 1.0173115730285645, "learning_rate": 0.0002, "epoch": 7.863247863247864, "step": 1380}, {"loss": 0.9764, "grad_norm": 1.0145931243896484, "learning_rate": 0.0002, "epoch": 7.92022792022792, "step": 1390}, {"loss": 0.9465, "grad_norm": 1.1547255516052246, "learning_rate": 0.0002, "epoch": 7.977207977207978, "step": 1400}]}