diff --git a/.gitattributes b/.gitattributes
index 91ed1dcbd4854689b7730daa09a270718fcbc0e9..295d77e2899184fa0a855f0100e981338d9fa84e 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -758,3 +758,12 @@ gemma-2-9b-it_int4_flare-multifin-en_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64
 gemma-2-9b-it_int4_flare-multifin-en_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-381-sd-10000/checkpoint-41/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-multifin-en_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-381-sd-10000/checkpoint-83/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-multifin-en_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-1.0-num-381-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..952cf5145a9d7e80dc7491c40196d56467129957
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34589486cf3edd2be3ba9bcb7e87563196b7a9856dd90683bdf986b557d160d3
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b5ed45857f07ffbbcce2f9410adbcf2cd60a5c8d
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883360fd592cf3f1cf085ec03770d65ae5241b54da17c86f6db6f4f70ce499a8
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a68155f67b0133f239047f7a2eb145441938bdff
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd7caf80bbf03bf5747a4ba0cc703529da16bea513682a4690f675e2e20cae3
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..025e69ad7f67d6a788b190469f6051bef8281138
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1375a54d766cb1abeca3dad9485f85b97541cebfc58a1329ef4d99ff69804a
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..62a919e1a561bd1a0770f96e1ccb1a54fd57180b
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae30aebcd5e08c368e71a3a77f80fbed9e73d7d4d684c7458f94879c2a9decfc
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a872649c2c697c66240121bb952ba312ae591f31
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/trainer_state.json
@@ -0,0 +1,1183 @@
+{
+  "best_metric": 0.5858802795410156,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1628,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 1.989741003354931e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..46eaef9a7fbc312796d355396116da61490c3b13
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f24b12fed305796f863449b57cd0ca3bea1dd442a5386a9d41f4b499b36f2a6
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1c0d955d1e84189853efefe27584e5e9f8f1f9cd
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6360e0676635c3589863b882bd927880b9ec693755297dfddcc3130175d2487
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8a019f0003f92dd6e57e5e23ac3a3287143e4b93
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f0860b0a43c49be22e2b9b0d95e29c108b949a5cb181307a11d81b37adc103
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..096cfabe688f366275d946a809aca82f5f0b7654
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a0e23ad59ba3c3d31a165bed1489745fdd8e1e429ffb2f2f32f2c1b0f676dd
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2f05fcc3bc72f85b8e52398bbc7a2ede782bc717
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/trainer_state.json
@@ -0,0 +1,1765 @@
+{
+  "best_metric": 0.49752503633499146,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 2442,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 2.984611505032397e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..57c25da613bb2eab59bfbe92e5288d113d8e3f61
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aaf02c68747e4e2e3ba81e34517865365822600ec522965f8661c772b87c326
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..417c816b8122705daa2420c003716555a4d3e9e7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1de34fd1171b91bc0438cda2d7077c8f3b303bbff2df442be3951728fa9d62d
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc18d93e2a50b75675b4a4dc3085ac8f7624db71
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e96e481c03422b79cfdd79b7439da0fa8a60de846a239e6cdcd715515b106b9
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ef656b45339a207e8b5d30d5d36c482c3394e9c6
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052b1bd34e6c16d4a674059140403503bdd5c083ad416c0d4553a3abac51e2d3
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..51b8ef89047f52ce2eb83abfcb96b7830d0aca1c
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/trainer_state.json
@@ -0,0 +1,2340 @@
+{
+  "best_metric": 0.4401616156101227,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 3256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    },
+    {
+      "epoch": 3.0098280098280097,
+      "grad_norm": 0.7644656896591187,
+      "learning_rate": 0.0002,
+      "loss": 0.4362,
+      "step": 2450
+    },
+    {
+      "epoch": 3.022113022113022,
+      "grad_norm": 0.9077525734901428,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0343980343980346,
+      "grad_norm": 0.7859287261962891,
+      "learning_rate": 0.0002,
+      "loss": 0.422,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0466830466830466,
+      "grad_norm": 1.1200323104858398,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 2480
+    },
+    {
+      "epoch": 3.058968058968059,
+      "grad_norm": 0.7570453882217407,
+      "learning_rate": 0.0002,
+      "loss": 0.4519,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0712530712530715,
+      "grad_norm": 0.9450915455818176,
+      "learning_rate": 0.0002,
+      "loss": 0.4351,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0835380835380835,
+      "grad_norm": 0.8303545117378235,
+      "learning_rate": 0.0002,
+      "loss": 0.4343,
+      "step": 2510
+    },
+    {
+      "epoch": 3.095823095823096,
+      "grad_norm": 0.8864443898200989,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2520
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.945324718952179,
+      "learning_rate": 0.0002,
+      "loss": 0.4601,
+      "step": 2530
+    },
+    {
+      "epoch": 3.1203931203931203,
+      "grad_norm": 1.0562494993209839,
+      "learning_rate": 0.0002,
+      "loss": 0.4345,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1326781326781328,
+      "grad_norm": 0.8607500195503235,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1449631449631448,
+      "grad_norm": 0.8719640374183655,
+      "learning_rate": 0.0002,
+      "loss": 0.456,
+      "step": 2560
+    },
+    {
+      "epoch": 3.157248157248157,
+      "grad_norm": 0.8647059202194214,
+      "learning_rate": 0.0002,
+      "loss": 0.4469,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1695331695331697,
+      "grad_norm": 0.8346507549285889,
+      "learning_rate": 0.0002,
+      "loss": 0.4483,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 1.0208854675292969,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 2590
+    },
+    {
+      "epoch": 3.194103194103194,
+      "grad_norm": 0.7064385414123535,
+      "learning_rate": 0.0002,
+      "loss": 0.435,
+      "step": 2600
+    },
+    {
+      "epoch": 3.2063882063882065,
+      "grad_norm": 0.927347719669342,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2186732186732185,
+      "grad_norm": 0.943517804145813,
+      "learning_rate": 0.0002,
+      "loss": 0.4561,
+      "step": 2620
+    },
+    {
+      "epoch": 3.230958230958231,
+      "grad_norm": 0.7837198376655579,
+      "learning_rate": 0.0002,
+      "loss": 0.4225,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.7752765417098999,
+      "learning_rate": 0.0002,
+      "loss": 0.4494,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2555282555282554,
+      "grad_norm": 0.8578953146934509,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2650
+    },
+    {
+      "epoch": 3.267813267813268,
+      "grad_norm": 1.0209529399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2800982800982803,
+      "grad_norm": 0.9069030284881592,
+      "learning_rate": 0.0002,
+      "loss": 0.4517,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2923832923832923,
+      "grad_norm": 0.8454729318618774,
+      "learning_rate": 0.0002,
+      "loss": 0.4262,
+      "step": 2680
+    },
+    {
+      "epoch": 3.3046683046683047,
+      "grad_norm": 0.8253099322319031,
+      "learning_rate": 0.0002,
+      "loss": 0.4349,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3169533169533167,
+      "grad_norm": 0.8765934109687805,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 2700
+    },
+    {
+      "epoch": 3.329238329238329,
+      "grad_norm": 0.8149126172065735,
+      "learning_rate": 0.0002,
+      "loss": 0.4518,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3415233415233416,
+      "grad_norm": 0.8820102214813232,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3538083538083536,
+      "grad_norm": 0.8813952803611755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 2730
+    },
+    {
+      "epoch": 3.366093366093366,
+      "grad_norm": 1.0338447093963623,
+      "learning_rate": 0.0002,
+      "loss": 0.4396,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8780209422111511,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2750
+    },
+    {
+      "epoch": 3.3906633906633905,
+      "grad_norm": 0.9017151594161987,
+      "learning_rate": 0.0002,
+      "loss": 0.441,
+      "step": 2760
+    },
+    {
+      "epoch": 3.402948402948403,
+      "grad_norm": 0.8647638559341431,
+      "learning_rate": 0.0002,
+      "loss": 0.446,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4152334152334154,
+      "grad_norm": 0.8298183679580688,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4275184275184274,
+      "grad_norm": 0.9298108816146851,
+      "learning_rate": 0.0002,
+      "loss": 0.4406,
+      "step": 2790
+    },
+    {
+      "epoch": 3.43980343980344,
+      "grad_norm": 0.8909980058670044,
+      "learning_rate": 0.0002,
+      "loss": 0.4145,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4520884520884523,
+      "grad_norm": 0.8027496933937073,
+      "learning_rate": 0.0002,
+      "loss": 0.4148,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4643734643734643,
+      "grad_norm": 0.8766195774078369,
+      "learning_rate": 0.0002,
+      "loss": 0.4244,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4766584766584767,
+      "grad_norm": 0.8194443583488464,
+      "learning_rate": 0.0002,
+      "loss": 0.4292,
+      "step": 2830
+    },
+    {
+      "epoch": 3.488943488943489,
+      "grad_norm": 0.9862873554229736,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 2840
+    },
+    {
+      "epoch": 3.501228501228501,
+      "grad_norm": 0.8755377531051636,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.7300266027450562,
+      "learning_rate": 0.0002,
+      "loss": 0.4231,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5257985257985256,
+      "grad_norm": 0.8342461585998535,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 2870
+    },
+    {
+      "epoch": 3.538083538083538,
+      "grad_norm": 0.8624151349067688,
+      "learning_rate": 0.0002,
+      "loss": 0.4395,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5503685503685505,
+      "grad_norm": 0.8931261301040649,
+      "learning_rate": 0.0002,
+      "loss": 0.4064,
+      "step": 2890
+    },
+    {
+      "epoch": 3.562653562653563,
+      "grad_norm": 0.8617086410522461,
+      "learning_rate": 0.0002,
+      "loss": 0.4358,
+      "step": 2900
+    },
+    {
+      "epoch": 3.574938574938575,
+      "grad_norm": 0.8754099607467651,
+      "learning_rate": 0.0002,
+      "loss": 0.419,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5872235872235874,
+      "grad_norm": 0.8345834612846375,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5995085995085994,
+      "grad_norm": 1.1414062976837158,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2930
+    },
+    {
+      "epoch": 3.611793611793612,
+      "grad_norm": 0.994860053062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4297,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6240786240786242,
+      "grad_norm": 1.19268000125885,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.8399543762207031,
+      "learning_rate": 0.0002,
+      "loss": 0.4029,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.9873217940330505,
+      "learning_rate": 0.0002,
+      "loss": 0.4432,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6609336609336607,
+      "grad_norm": 0.9116013646125793,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2980
+    },
+    {
+      "epoch": 3.673218673218673,
+      "grad_norm": 0.9503833651542664,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6855036855036856,
+      "grad_norm": 0.9401112794876099,
+      "learning_rate": 0.0002,
+      "loss": 0.4306,
+      "step": 3000
+    },
+    {
+      "epoch": 3.697788697788698,
+      "grad_norm": 1.00745689868927,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 3010
+    },
+    {
+      "epoch": 3.71007371007371,
+      "grad_norm": 1.0553191900253296,
+      "learning_rate": 0.0002,
+      "loss": 0.432,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7223587223587224,
+      "grad_norm": 1.0226953029632568,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 3030
+    },
+    {
+      "epoch": 3.7346437346437344,
+      "grad_norm": 1.085554838180542,
+      "learning_rate": 0.0002,
+      "loss": 0.418,
+      "step": 3040
+    },
+    {
+      "epoch": 3.746928746928747,
+      "grad_norm": 0.9948731064796448,
+      "learning_rate": 0.0002,
+      "loss": 0.4196,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7592137592137593,
+      "grad_norm": 0.9328727126121521,
+      "learning_rate": 0.0002,
+      "loss": 0.4281,
+      "step": 3060
+    },
+    {
+      "epoch": 3.7714987714987718,
+      "grad_norm": 1.0533266067504883,
+      "learning_rate": 0.0002,
+      "loss": 0.4284,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.8213809132575989,
+      "learning_rate": 0.0002,
+      "loss": 0.4414,
+      "step": 3080
+    },
+    {
+      "epoch": 3.796068796068796,
+      "grad_norm": 0.8941594362258911,
+      "learning_rate": 0.0002,
+      "loss": 0.4348,
+      "step": 3090
+    },
+    {
+      "epoch": 3.808353808353808,
+      "grad_norm": 0.8324518203735352,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8206388206388207,
+      "grad_norm": 0.8811233639717102,
+      "learning_rate": 0.0002,
+      "loss": 0.4227,
+      "step": 3110
+    },
+    {
+      "epoch": 3.832923832923833,
+      "grad_norm": 0.8781470060348511,
+      "learning_rate": 0.0002,
+      "loss": 0.4195,
+      "step": 3120
+    },
+    {
+      "epoch": 3.845208845208845,
+      "grad_norm": 0.8994116187095642,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 3130
+    },
+    {
+      "epoch": 3.8574938574938575,
+      "grad_norm": 0.8605017066001892,
+      "learning_rate": 0.0002,
+      "loss": 0.4149,
+      "step": 3140
+    },
+    {
+      "epoch": 3.8697788697788695,
+      "grad_norm": 0.8966400027275085,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 3150
+    },
+    {
+      "epoch": 3.882063882063882,
+      "grad_norm": 0.8856554627418518,
+      "learning_rate": 0.0002,
+      "loss": 0.4245,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8943488943488944,
+      "grad_norm": 0.8971620798110962,
+      "learning_rate": 0.0002,
+      "loss": 0.4101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.906633906633907,
+      "grad_norm": 0.9807813167572021,
+      "learning_rate": 0.0002,
+      "loss": 0.3993,
+      "step": 3180
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.8614121675491333,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9312039312039313,
+      "grad_norm": 0.989171028137207,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9434889434889433,
+      "grad_norm": 0.8168872594833374,
+      "learning_rate": 0.0002,
+      "loss": 0.4182,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9557739557739557,
+      "grad_norm": 0.8109386563301086,
+      "learning_rate": 0.0002,
+      "loss": 0.4112,
+      "step": 3220
+    },
+    {
+      "epoch": 3.968058968058968,
+      "grad_norm": 1.0175853967666626,
+      "learning_rate": 0.0002,
+      "loss": 0.4165,
+      "step": 3230
+    },
+    {
+      "epoch": 3.98034398034398,
+      "grad_norm": 0.936143159866333,
+      "learning_rate": 0.0002,
+      "loss": 0.4146,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9926289926289926,
+      "grad_norm": 0.9557915925979614,
+      "learning_rate": 0.0002,
+      "loss": 0.4163,
+      "step": 3250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4401616156101227,
+      "eval_runtime": 20.8047,
+      "eval_samples_per_second": 15.91,
+      "eval_steps_per_second": 2.019,
+      "step": 3256
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 3.979482006709862e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4dda251d96712ace49699a3e1887545dcaab5b60
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b154e3c9ff723f8964d80fb6716a2a5235fdd4102c7877cb3e9efa7fc1697b4
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9deb5105b82a76bcdcfc50284cccef1da2185187
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb292829920897a5d39a38ed5a6be6013bb568f65f6dd09c3fc76d9afbe4b17
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..60ff9b2a12b630e20a5573d41a49c10355cab5c6
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f690b2b370d5088d36b551f18fabfa9ce1a4948c7688bca4601e27707c6a691
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dd4d3dc7ab541de64c7cd8d5eddfe0c7f7c2daea
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658ed4b5e4b2f574242efa0fcb5a3d72b4a37a60e9d7c28715ade14b38c49030
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f56a06a08c681a18e89a79f45f6f5a1430dbdb11
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/trainer_state.json
@@ -0,0 +1,2922 @@
+{
+  "best_metric": 0.4017423093318939,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070",
+  "epoch": 5.0,
+  "eval_steps": 10,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    },
+    {
+      "epoch": 3.0098280098280097,
+      "grad_norm": 0.7644656896591187,
+      "learning_rate": 0.0002,
+      "loss": 0.4362,
+      "step": 2450
+    },
+    {
+      "epoch": 3.022113022113022,
+      "grad_norm": 0.9077525734901428,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0343980343980346,
+      "grad_norm": 0.7859287261962891,
+      "learning_rate": 0.0002,
+      "loss": 0.422,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0466830466830466,
+      "grad_norm": 1.1200323104858398,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 2480
+    },
+    {
+      "epoch": 3.058968058968059,
+      "grad_norm": 0.7570453882217407,
+      "learning_rate": 0.0002,
+      "loss": 0.4519,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0712530712530715,
+      "grad_norm": 0.9450915455818176,
+      "learning_rate": 0.0002,
+      "loss": 0.4351,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0835380835380835,
+      "grad_norm": 0.8303545117378235,
+      "learning_rate": 0.0002,
+      "loss": 0.4343,
+      "step": 2510
+    },
+    {
+      "epoch": 3.095823095823096,
+      "grad_norm": 0.8864443898200989,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2520
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.945324718952179,
+      "learning_rate": 0.0002,
+      "loss": 0.4601,
+      "step": 2530
+    },
+    {
+      "epoch": 3.1203931203931203,
+      "grad_norm": 1.0562494993209839,
+      "learning_rate": 0.0002,
+      "loss": 0.4345,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1326781326781328,
+      "grad_norm": 0.8607500195503235,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1449631449631448,
+      "grad_norm": 0.8719640374183655,
+      "learning_rate": 0.0002,
+      "loss": 0.456,
+      "step": 2560
+    },
+    {
+      "epoch": 3.157248157248157,
+      "grad_norm": 0.8647059202194214,
+      "learning_rate": 0.0002,
+      "loss": 0.4469,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1695331695331697,
+      "grad_norm": 0.8346507549285889,
+      "learning_rate": 0.0002,
+      "loss": 0.4483,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 1.0208854675292969,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 2590
+    },
+    {
+      "epoch": 3.194103194103194,
+      "grad_norm": 0.7064385414123535,
+      "learning_rate": 0.0002,
+      "loss": 0.435,
+      "step": 2600
+    },
+    {
+      "epoch": 3.2063882063882065,
+      "grad_norm": 0.927347719669342,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2186732186732185,
+      "grad_norm": 0.943517804145813,
+      "learning_rate": 0.0002,
+      "loss": 0.4561,
+      "step": 2620
+    },
+    {
+      "epoch": 3.230958230958231,
+      "grad_norm": 0.7837198376655579,
+      "learning_rate": 0.0002,
+      "loss": 0.4225,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.7752765417098999,
+      "learning_rate": 0.0002,
+      "loss": 0.4494,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2555282555282554,
+      "grad_norm": 0.8578953146934509,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2650
+    },
+    {
+      "epoch": 3.267813267813268,
+      "grad_norm": 1.0209529399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2800982800982803,
+      "grad_norm": 0.9069030284881592,
+      "learning_rate": 0.0002,
+      "loss": 0.4517,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2923832923832923,
+      "grad_norm": 0.8454729318618774,
+      "learning_rate": 0.0002,
+      "loss": 0.4262,
+      "step": 2680
+    },
+    {
+      "epoch": 3.3046683046683047,
+      "grad_norm": 0.8253099322319031,
+      "learning_rate": 0.0002,
+      "loss": 0.4349,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3169533169533167,
+      "grad_norm": 0.8765934109687805,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 2700
+    },
+    {
+      "epoch": 3.329238329238329,
+      "grad_norm": 0.8149126172065735,
+      "learning_rate": 0.0002,
+      "loss": 0.4518,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3415233415233416,
+      "grad_norm": 0.8820102214813232,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3538083538083536,
+      "grad_norm": 0.8813952803611755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 2730
+    },
+    {
+      "epoch": 3.366093366093366,
+      "grad_norm": 1.0338447093963623,
+      "learning_rate": 0.0002,
+      "loss": 0.4396,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8780209422111511,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2750
+    },
+    {
+      "epoch": 3.3906633906633905,
+      "grad_norm": 0.9017151594161987,
+      "learning_rate": 0.0002,
+      "loss": 0.441,
+      "step": 2760
+    },
+    {
+      "epoch": 3.402948402948403,
+      "grad_norm": 0.8647638559341431,
+      "learning_rate": 0.0002,
+      "loss": 0.446,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4152334152334154,
+      "grad_norm": 0.8298183679580688,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4275184275184274,
+      "grad_norm": 0.9298108816146851,
+      "learning_rate": 0.0002,
+      "loss": 0.4406,
+      "step": 2790
+    },
+    {
+      "epoch": 3.43980343980344,
+      "grad_norm": 0.8909980058670044,
+      "learning_rate": 0.0002,
+      "loss": 0.4145,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4520884520884523,
+      "grad_norm": 0.8027496933937073,
+      "learning_rate": 0.0002,
+      "loss": 0.4148,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4643734643734643,
+      "grad_norm": 0.8766195774078369,
+      "learning_rate": 0.0002,
+      "loss": 0.4244,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4766584766584767,
+      "grad_norm": 0.8194443583488464,
+      "learning_rate": 0.0002,
+      "loss": 0.4292,
+      "step": 2830
+    },
+    {
+      "epoch": 3.488943488943489,
+      "grad_norm": 0.9862873554229736,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 2840
+    },
+    {
+      "epoch": 3.501228501228501,
+      "grad_norm": 0.8755377531051636,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.7300266027450562,
+      "learning_rate": 0.0002,
+      "loss": 0.4231,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5257985257985256,
+      "grad_norm": 0.8342461585998535,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 2870
+    },
+    {
+      "epoch": 3.538083538083538,
+      "grad_norm": 0.8624151349067688,
+      "learning_rate": 0.0002,
+      "loss": 0.4395,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5503685503685505,
+      "grad_norm": 0.8931261301040649,
+      "learning_rate": 0.0002,
+      "loss": 0.4064,
+      "step": 2890
+    },
+    {
+      "epoch": 3.562653562653563,
+      "grad_norm": 0.8617086410522461,
+      "learning_rate": 0.0002,
+      "loss": 0.4358,
+      "step": 2900
+    },
+    {
+      "epoch": 3.574938574938575,
+      "grad_norm": 0.8754099607467651,
+      "learning_rate": 0.0002,
+      "loss": 0.419,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5872235872235874,
+      "grad_norm": 0.8345834612846375,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5995085995085994,
+      "grad_norm": 1.1414062976837158,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2930
+    },
+    {
+      "epoch": 3.611793611793612,
+      "grad_norm": 0.994860053062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4297,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6240786240786242,
+      "grad_norm": 1.19268000125885,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.8399543762207031,
+      "learning_rate": 0.0002,
+      "loss": 0.4029,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.9873217940330505,
+      "learning_rate": 0.0002,
+      "loss": 0.4432,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6609336609336607,
+      "grad_norm": 0.9116013646125793,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2980
+    },
+    {
+      "epoch": 3.673218673218673,
+      "grad_norm": 0.9503833651542664,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6855036855036856,
+      "grad_norm": 0.9401112794876099,
+      "learning_rate": 0.0002,
+      "loss": 0.4306,
+      "step": 3000
+    },
+    {
+      "epoch": 3.697788697788698,
+      "grad_norm": 1.00745689868927,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 3010
+    },
+    {
+      "epoch": 3.71007371007371,
+      "grad_norm": 1.0553191900253296,
+      "learning_rate": 0.0002,
+      "loss": 0.432,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7223587223587224,
+      "grad_norm": 1.0226953029632568,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 3030
+    },
+    {
+      "epoch": 3.7346437346437344,
+      "grad_norm": 1.085554838180542,
+      "learning_rate": 0.0002,
+      "loss": 0.418,
+      "step": 3040
+    },
+    {
+      "epoch": 3.746928746928747,
+      "grad_norm": 0.9948731064796448,
+      "learning_rate": 0.0002,
+      "loss": 0.4196,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7592137592137593,
+      "grad_norm": 0.9328727126121521,
+      "learning_rate": 0.0002,
+      "loss": 0.4281,
+      "step": 3060
+    },
+    {
+      "epoch": 3.7714987714987718,
+      "grad_norm": 1.0533266067504883,
+      "learning_rate": 0.0002,
+      "loss": 0.4284,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.8213809132575989,
+      "learning_rate": 0.0002,
+      "loss": 0.4414,
+      "step": 3080
+    },
+    {
+      "epoch": 3.796068796068796,
+      "grad_norm": 0.8941594362258911,
+      "learning_rate": 0.0002,
+      "loss": 0.4348,
+      "step": 3090
+    },
+    {
+      "epoch": 3.808353808353808,
+      "grad_norm": 0.8324518203735352,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8206388206388207,
+      "grad_norm": 0.8811233639717102,
+      "learning_rate": 0.0002,
+      "loss": 0.4227,
+      "step": 3110
+    },
+    {
+      "epoch": 3.832923832923833,
+      "grad_norm": 0.8781470060348511,
+      "learning_rate": 0.0002,
+      "loss": 0.4195,
+      "step": 3120
+    },
+    {
+      "epoch": 3.845208845208845,
+      "grad_norm": 0.8994116187095642,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 3130
+    },
+    {
+      "epoch": 3.8574938574938575,
+      "grad_norm": 0.8605017066001892,
+      "learning_rate": 0.0002,
+      "loss": 0.4149,
+      "step": 3140
+    },
+    {
+      "epoch": 3.8697788697788695,
+      "grad_norm": 0.8966400027275085,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 3150
+    },
+    {
+      "epoch": 3.882063882063882,
+      "grad_norm": 0.8856554627418518,
+      "learning_rate": 0.0002,
+      "loss": 0.4245,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8943488943488944,
+      "grad_norm": 0.8971620798110962,
+      "learning_rate": 0.0002,
+      "loss": 0.4101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.906633906633907,
+      "grad_norm": 0.9807813167572021,
+      "learning_rate": 0.0002,
+      "loss": 0.3993,
+      "step": 3180
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.8614121675491333,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9312039312039313,
+      "grad_norm": 0.989171028137207,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9434889434889433,
+      "grad_norm": 0.8168872594833374,
+      "learning_rate": 0.0002,
+      "loss": 0.4182,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9557739557739557,
+      "grad_norm": 0.8109386563301086,
+      "learning_rate": 0.0002,
+      "loss": 0.4112,
+      "step": 3220
+    },
+    {
+      "epoch": 3.968058968058968,
+      "grad_norm": 1.0175853967666626,
+      "learning_rate": 0.0002,
+      "loss": 0.4165,
+      "step": 3230
+    },
+    {
+      "epoch": 3.98034398034398,
+      "grad_norm": 0.936143159866333,
+      "learning_rate": 0.0002,
+      "loss": 0.4146,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9926289926289926,
+      "grad_norm": 0.9557915925979614,
+      "learning_rate": 0.0002,
+      "loss": 0.4163,
+      "step": 3250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4401616156101227,
+      "eval_runtime": 20.8047,
+      "eval_samples_per_second": 15.91,
+      "eval_steps_per_second": 2.019,
+      "step": 3256
+    },
+    {
+      "epoch": 4.004914004914005,
+      "grad_norm": 0.7590614557266235,
+      "learning_rate": 0.0002,
+      "loss": 0.408,
+      "step": 3260
+    },
+    {
+      "epoch": 4.017199017199017,
+      "grad_norm": 0.8920791149139404,
+      "learning_rate": 0.0002,
+      "loss": 0.4001,
+      "step": 3270
+    },
+    {
+      "epoch": 4.0294840294840295,
+      "grad_norm": 0.8640421628952026,
+      "learning_rate": 0.0002,
+      "loss": 0.3789,
+      "step": 3280
+    },
+    {
+      "epoch": 4.041769041769042,
+      "grad_norm": 0.9074113965034485,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3290
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 1.0600885152816772,
+      "learning_rate": 0.0002,
+      "loss": 0.3728,
+      "step": 3300
+    },
+    {
+      "epoch": 4.066339066339066,
+      "grad_norm": 0.9682773351669312,
+      "learning_rate": 0.0002,
+      "loss": 0.3857,
+      "step": 3310
+    },
+    {
+      "epoch": 4.078624078624078,
+      "grad_norm": 0.9326395392417908,
+      "learning_rate": 0.0002,
+      "loss": 0.4007,
+      "step": 3320
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.8886597156524658,
+      "learning_rate": 0.0002,
+      "loss": 0.3823,
+      "step": 3330
+    },
+    {
+      "epoch": 4.103194103194103,
+      "grad_norm": 1.032205581665039,
+      "learning_rate": 0.0002,
+      "loss": 0.3929,
+      "step": 3340
+    },
+    {
+      "epoch": 4.115479115479116,
+      "grad_norm": 0.8669408559799194,
+      "learning_rate": 0.0002,
+      "loss": 0.3836,
+      "step": 3350
+    },
+    {
+      "epoch": 4.127764127764128,
+      "grad_norm": 0.8250347971916199,
+      "learning_rate": 0.0002,
+      "loss": 0.3866,
+      "step": 3360
+    },
+    {
+      "epoch": 4.14004914004914,
+      "grad_norm": 0.7919842600822449,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3370
+    },
+    {
+      "epoch": 4.152334152334152,
+      "grad_norm": 1.045682430267334,
+      "learning_rate": 0.0002,
+      "loss": 0.3838,
+      "step": 3380
+    },
+    {
+      "epoch": 4.164619164619165,
+      "grad_norm": 0.6873571276664734,
+      "learning_rate": 0.0002,
+      "loss": 0.3796,
+      "step": 3390
+    },
+    {
+      "epoch": 4.176904176904177,
+      "grad_norm": 1.0227675437927246,
+      "learning_rate": 0.0002,
+      "loss": 0.3942,
+      "step": 3400
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 0.9167711734771729,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 3410
+    },
+    {
+      "epoch": 4.201474201474202,
+      "grad_norm": 1.0598796606063843,
+      "learning_rate": 0.0002,
+      "loss": 0.3792,
+      "step": 3420
+    },
+    {
+      "epoch": 4.2137592137592135,
+      "grad_norm": 0.8581843972206116,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3430
+    },
+    {
+      "epoch": 4.226044226044226,
+      "grad_norm": 0.8862360119819641,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3440
+    },
+    {
+      "epoch": 4.238329238329238,
+      "grad_norm": 1.0248323678970337,
+      "learning_rate": 0.0002,
+      "loss": 0.3889,
+      "step": 3450
+    },
+    {
+      "epoch": 4.250614250614251,
+      "grad_norm": 0.8746261596679688,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3460
+    },
+    {
+      "epoch": 4.262899262899263,
+      "grad_norm": 0.7442536354064941,
+      "learning_rate": 0.0002,
+      "loss": 0.3949,
+      "step": 3470
+    },
+    {
+      "epoch": 4.275184275184275,
+      "grad_norm": 0.8295119404792786,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3480
+    },
+    {
+      "epoch": 4.287469287469287,
+      "grad_norm": 1.0634245872497559,
+      "learning_rate": 0.0002,
+      "loss": 0.3895,
+      "step": 3490
+    },
+    {
+      "epoch": 4.2997542997543,
+      "grad_norm": 0.9554621577262878,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3500
+    },
+    {
+      "epoch": 4.312039312039312,
+      "grad_norm": 1.0191723108291626,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3510
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.8573611378669739,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 3520
+    },
+    {
+      "epoch": 4.336609336609337,
+      "grad_norm": 0.9082390069961548,
+      "learning_rate": 0.0002,
+      "loss": 0.3869,
+      "step": 3530
+    },
+    {
+      "epoch": 4.348894348894349,
+      "grad_norm": 0.8650212287902832,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3540
+    },
+    {
+      "epoch": 4.361179361179361,
+      "grad_norm": 0.7186297178268433,
+      "learning_rate": 0.0002,
+      "loss": 0.3915,
+      "step": 3550
+    },
+    {
+      "epoch": 4.3734643734643734,
+      "grad_norm": 0.9750986695289612,
+      "learning_rate": 0.0002,
+      "loss": 0.3861,
+      "step": 3560
+    },
+    {
+      "epoch": 4.385749385749386,
+      "grad_norm": 1.0710467100143433,
+      "learning_rate": 0.0002,
+      "loss": 0.3967,
+      "step": 3570
+    },
+    {
+      "epoch": 4.398034398034398,
+      "grad_norm": 0.7974869012832642,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3580
+    },
+    {
+      "epoch": 4.41031941031941,
+      "grad_norm": 0.9405913949012756,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3590
+    },
+    {
+      "epoch": 4.422604422604422,
+      "grad_norm": 0.9393602609634399,
+      "learning_rate": 0.0002,
+      "loss": 0.3982,
+      "step": 3600
+    },
+    {
+      "epoch": 4.434889434889435,
+      "grad_norm": 1.0798007249832153,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 3610
+    },
+    {
+      "epoch": 4.447174447174447,
+      "grad_norm": 0.9226186275482178,
+      "learning_rate": 0.0002,
+      "loss": 0.3682,
+      "step": 3620
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 1.1046524047851562,
+      "learning_rate": 0.0002,
+      "loss": 0.3742,
+      "step": 3630
+    },
+    {
+      "epoch": 4.471744471744472,
+      "grad_norm": 0.8848567605018616,
+      "learning_rate": 0.0002,
+      "loss": 0.3886,
+      "step": 3640
+    },
+    {
+      "epoch": 4.484029484029484,
+      "grad_norm": 0.8913224339485168,
+      "learning_rate": 0.0002,
+      "loss": 0.3848,
+      "step": 3650
+    },
+    {
+      "epoch": 4.496314496314496,
+      "grad_norm": 0.8497583270072937,
+      "learning_rate": 0.0002,
+      "loss": 0.3731,
+      "step": 3660
+    },
+    {
+      "epoch": 4.5085995085995085,
+      "grad_norm": 0.8263831734657288,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 3670
+    },
+    {
+      "epoch": 4.520884520884521,
+      "grad_norm": 0.8470269441604614,
+      "learning_rate": 0.0002,
+      "loss": 0.3815,
+      "step": 3680
+    },
+    {
+      "epoch": 4.533169533169533,
+      "grad_norm": 0.860038161277771,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3690
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.8898552656173706,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3700
+    },
+    {
+      "epoch": 4.557739557739557,
+      "grad_norm": 0.8152070641517639,
+      "learning_rate": 0.0002,
+      "loss": 0.3776,
+      "step": 3710
+    },
+    {
+      "epoch": 4.57002457002457,
+      "grad_norm": 0.7847675085067749,
+      "learning_rate": 0.0002,
+      "loss": 0.383,
+      "step": 3720
+    },
+    {
+      "epoch": 4.582309582309582,
+      "grad_norm": 0.9625533819198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3730
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.9097456336021423,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 3740
+    },
+    {
+      "epoch": 4.606879606879607,
+      "grad_norm": 0.871329128742218,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 3750
+    },
+    {
+      "epoch": 4.61916461916462,
+      "grad_norm": 0.9879975914955139,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 3760
+    },
+    {
+      "epoch": 4.631449631449631,
+      "grad_norm": 0.8636731505393982,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3770
+    },
+    {
+      "epoch": 4.643734643734644,
+      "grad_norm": 1.0488964319229126,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 3780
+    },
+    {
+      "epoch": 4.656019656019656,
+      "grad_norm": 0.7637056112289429,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3790
+    },
+    {
+      "epoch": 4.6683046683046685,
+      "grad_norm": 0.8507546186447144,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 3800
+    },
+    {
+      "epoch": 4.680589680589681,
+      "grad_norm": 1.0216856002807617,
+      "learning_rate": 0.0002,
+      "loss": 0.3852,
+      "step": 3810
+    },
+    {
+      "epoch": 4.6928746928746925,
+      "grad_norm": 1.026343822479248,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 3820
+    },
+    {
+      "epoch": 4.705159705159705,
+      "grad_norm": 0.8311620950698853,
+      "learning_rate": 0.0002,
+      "loss": 0.3687,
+      "step": 3830
+    },
+    {
+      "epoch": 4.717444717444717,
+      "grad_norm": 0.7770653367042542,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 3840
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 0.7616215348243713,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3850
+    },
+    {
+      "epoch": 4.742014742014742,
+      "grad_norm": 1.0377072095870972,
+      "learning_rate": 0.0002,
+      "loss": 0.3927,
+      "step": 3860
+    },
+    {
+      "epoch": 4.754299754299755,
+      "grad_norm": 0.9713505506515503,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 3870
+    },
+    {
+      "epoch": 4.766584766584766,
+      "grad_norm": 0.8803321719169617,
+      "learning_rate": 0.0002,
+      "loss": 0.3722,
+      "step": 3880
+    },
+    {
+      "epoch": 4.778869778869779,
+      "grad_norm": 0.885535478591919,
+      "learning_rate": 0.0002,
+      "loss": 0.3756,
+      "step": 3890
+    },
+    {
+      "epoch": 4.791154791154791,
+      "grad_norm": 1.0877983570098877,
+      "learning_rate": 0.0002,
+      "loss": 0.3714,
+      "step": 3900
+    },
+    {
+      "epoch": 4.803439803439804,
+      "grad_norm": 0.7875366806983948,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3910
+    },
+    {
+      "epoch": 4.815724815724816,
+      "grad_norm": 0.8550102114677429,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 3920
+    },
+    {
+      "epoch": 4.828009828009828,
+      "grad_norm": 1.0217846632003784,
+      "learning_rate": 0.0002,
+      "loss": 0.3716,
+      "step": 3930
+    },
+    {
+      "epoch": 4.84029484029484,
+      "grad_norm": 0.7315713167190552,
+      "learning_rate": 0.0002,
+      "loss": 0.3649,
+      "step": 3940
+    },
+    {
+      "epoch": 4.8525798525798525,
+      "grad_norm": 0.8924923539161682,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3950
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 0.9730218052864075,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 3960
+    },
+    {
+      "epoch": 4.877149877149877,
+      "grad_norm": 0.9202003479003906,
+      "learning_rate": 0.0002,
+      "loss": 0.3705,
+      "step": 3970
+    },
+    {
+      "epoch": 4.88943488943489,
+      "grad_norm": 0.8173081874847412,
+      "learning_rate": 0.0002,
+      "loss": 0.3617,
+      "step": 3980
+    },
+    {
+      "epoch": 4.901719901719901,
+      "grad_norm": 0.7178564667701721,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3990
+    },
+    {
+      "epoch": 4.914004914004914,
+      "grad_norm": 0.913684606552124,
+      "learning_rate": 0.0002,
+      "loss": 0.3768,
+      "step": 4000
+    },
+    {
+      "epoch": 4.926289926289926,
+      "grad_norm": 0.8817896842956543,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 4010
+    },
+    {
+      "epoch": 4.938574938574939,
+      "grad_norm": 0.7652186751365662,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 4020
+    },
+    {
+      "epoch": 4.950859950859951,
+      "grad_norm": 0.8828630447387695,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 4030
+    },
+    {
+      "epoch": 4.963144963144963,
+      "grad_norm": 1.0878605842590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3672,
+      "step": 4040
+    },
+    {
+      "epoch": 4.975429975429975,
+      "grad_norm": 1.0845288038253784,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 4050
+    },
+    {
+      "epoch": 4.987714987714988,
+      "grad_norm": 0.8431115746498108,
+      "learning_rate": 0.0002,
+      "loss": 0.365,
+      "step": 4060
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8320387601852417,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4070
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.4017423093318939,
+      "eval_runtime": 20.8466,
+      "eval_samples_per_second": 15.878,
+      "eval_steps_per_second": 2.015,
+      "step": 4070
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 4.974352508387328e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..baf6e9f88a0c9d2a9eefbfd9a9a9fb3432594c5b
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b71f08f91e7f50824a7b20915352bfe127f0aa2a852d5e31428e46126e1dedf
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4283d8b55c14ba4bcbfd4417e3b1cdbaf4788bb9
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed23e6dc5cbc64d25655776d5050752680cf8a6479df149be0120c5af55e41d2
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e1bf1b9933f9db104c66a846d993e818a981fb6
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89bfaad1caf651786ff92906ce5950787dae1956b71d26219ecdc6457e0c501
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f42d47f14a3fb30b00dc602a4c235bfb0a15c115
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32595ef5e315cec2f7af25630a1aa9d39273a49cd98efb5d698e0b329b0096be
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d47cd64a02a98a650c32189036fd2c70459aab42
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/trainer_state.json
@@ -0,0 +1,3497 @@
+{
+  "best_metric": 0.3778059184551239,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 4884,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    },
+    {
+      "epoch": 3.0098280098280097,
+      "grad_norm": 0.7644656896591187,
+      "learning_rate": 0.0002,
+      "loss": 0.4362,
+      "step": 2450
+    },
+    {
+      "epoch": 3.022113022113022,
+      "grad_norm": 0.9077525734901428,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0343980343980346,
+      "grad_norm": 0.7859287261962891,
+      "learning_rate": 0.0002,
+      "loss": 0.422,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0466830466830466,
+      "grad_norm": 1.1200323104858398,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 2480
+    },
+    {
+      "epoch": 3.058968058968059,
+      "grad_norm": 0.7570453882217407,
+      "learning_rate": 0.0002,
+      "loss": 0.4519,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0712530712530715,
+      "grad_norm": 0.9450915455818176,
+      "learning_rate": 0.0002,
+      "loss": 0.4351,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0835380835380835,
+      "grad_norm": 0.8303545117378235,
+      "learning_rate": 0.0002,
+      "loss": 0.4343,
+      "step": 2510
+    },
+    {
+      "epoch": 3.095823095823096,
+      "grad_norm": 0.8864443898200989,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2520
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.945324718952179,
+      "learning_rate": 0.0002,
+      "loss": 0.4601,
+      "step": 2530
+    },
+    {
+      "epoch": 3.1203931203931203,
+      "grad_norm": 1.0562494993209839,
+      "learning_rate": 0.0002,
+      "loss": 0.4345,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1326781326781328,
+      "grad_norm": 0.8607500195503235,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1449631449631448,
+      "grad_norm": 0.8719640374183655,
+      "learning_rate": 0.0002,
+      "loss": 0.456,
+      "step": 2560
+    },
+    {
+      "epoch": 3.157248157248157,
+      "grad_norm": 0.8647059202194214,
+      "learning_rate": 0.0002,
+      "loss": 0.4469,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1695331695331697,
+      "grad_norm": 0.8346507549285889,
+      "learning_rate": 0.0002,
+      "loss": 0.4483,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 1.0208854675292969,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 2590
+    },
+    {
+      "epoch": 3.194103194103194,
+      "grad_norm": 0.7064385414123535,
+      "learning_rate": 0.0002,
+      "loss": 0.435,
+      "step": 2600
+    },
+    {
+      "epoch": 3.2063882063882065,
+      "grad_norm": 0.927347719669342,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2186732186732185,
+      "grad_norm": 0.943517804145813,
+      "learning_rate": 0.0002,
+      "loss": 0.4561,
+      "step": 2620
+    },
+    {
+      "epoch": 3.230958230958231,
+      "grad_norm": 0.7837198376655579,
+      "learning_rate": 0.0002,
+      "loss": 0.4225,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.7752765417098999,
+      "learning_rate": 0.0002,
+      "loss": 0.4494,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2555282555282554,
+      "grad_norm": 0.8578953146934509,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2650
+    },
+    {
+      "epoch": 3.267813267813268,
+      "grad_norm": 1.0209529399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2800982800982803,
+      "grad_norm": 0.9069030284881592,
+      "learning_rate": 0.0002,
+      "loss": 0.4517,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2923832923832923,
+      "grad_norm": 0.8454729318618774,
+      "learning_rate": 0.0002,
+      "loss": 0.4262,
+      "step": 2680
+    },
+    {
+      "epoch": 3.3046683046683047,
+      "grad_norm": 0.8253099322319031,
+      "learning_rate": 0.0002,
+      "loss": 0.4349,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3169533169533167,
+      "grad_norm": 0.8765934109687805,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 2700
+    },
+    {
+      "epoch": 3.329238329238329,
+      "grad_norm": 0.8149126172065735,
+      "learning_rate": 0.0002,
+      "loss": 0.4518,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3415233415233416,
+      "grad_norm": 0.8820102214813232,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3538083538083536,
+      "grad_norm": 0.8813952803611755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 2730
+    },
+    {
+      "epoch": 3.366093366093366,
+      "grad_norm": 1.0338447093963623,
+      "learning_rate": 0.0002,
+      "loss": 0.4396,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8780209422111511,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2750
+    },
+    {
+      "epoch": 3.3906633906633905,
+      "grad_norm": 0.9017151594161987,
+      "learning_rate": 0.0002,
+      "loss": 0.441,
+      "step": 2760
+    },
+    {
+      "epoch": 3.402948402948403,
+      "grad_norm": 0.8647638559341431,
+      "learning_rate": 0.0002,
+      "loss": 0.446,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4152334152334154,
+      "grad_norm": 0.8298183679580688,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4275184275184274,
+      "grad_norm": 0.9298108816146851,
+      "learning_rate": 0.0002,
+      "loss": 0.4406,
+      "step": 2790
+    },
+    {
+      "epoch": 3.43980343980344,
+      "grad_norm": 0.8909980058670044,
+      "learning_rate": 0.0002,
+      "loss": 0.4145,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4520884520884523,
+      "grad_norm": 0.8027496933937073,
+      "learning_rate": 0.0002,
+      "loss": 0.4148,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4643734643734643,
+      "grad_norm": 0.8766195774078369,
+      "learning_rate": 0.0002,
+      "loss": 0.4244,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4766584766584767,
+      "grad_norm": 0.8194443583488464,
+      "learning_rate": 0.0002,
+      "loss": 0.4292,
+      "step": 2830
+    },
+    {
+      "epoch": 3.488943488943489,
+      "grad_norm": 0.9862873554229736,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 2840
+    },
+    {
+      "epoch": 3.501228501228501,
+      "grad_norm": 0.8755377531051636,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.7300266027450562,
+      "learning_rate": 0.0002,
+      "loss": 0.4231,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5257985257985256,
+      "grad_norm": 0.8342461585998535,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 2870
+    },
+    {
+      "epoch": 3.538083538083538,
+      "grad_norm": 0.8624151349067688,
+      "learning_rate": 0.0002,
+      "loss": 0.4395,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5503685503685505,
+      "grad_norm": 0.8931261301040649,
+      "learning_rate": 0.0002,
+      "loss": 0.4064,
+      "step": 2890
+    },
+    {
+      "epoch": 3.562653562653563,
+      "grad_norm": 0.8617086410522461,
+      "learning_rate": 0.0002,
+      "loss": 0.4358,
+      "step": 2900
+    },
+    {
+      "epoch": 3.574938574938575,
+      "grad_norm": 0.8754099607467651,
+      "learning_rate": 0.0002,
+      "loss": 0.419,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5872235872235874,
+      "grad_norm": 0.8345834612846375,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5995085995085994,
+      "grad_norm": 1.1414062976837158,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2930
+    },
+    {
+      "epoch": 3.611793611793612,
+      "grad_norm": 0.994860053062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4297,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6240786240786242,
+      "grad_norm": 1.19268000125885,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.8399543762207031,
+      "learning_rate": 0.0002,
+      "loss": 0.4029,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.9873217940330505,
+      "learning_rate": 0.0002,
+      "loss": 0.4432,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6609336609336607,
+      "grad_norm": 0.9116013646125793,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2980
+    },
+    {
+      "epoch": 3.673218673218673,
+      "grad_norm": 0.9503833651542664,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6855036855036856,
+      "grad_norm": 0.9401112794876099,
+      "learning_rate": 0.0002,
+      "loss": 0.4306,
+      "step": 3000
+    },
+    {
+      "epoch": 3.697788697788698,
+      "grad_norm": 1.00745689868927,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 3010
+    },
+    {
+      "epoch": 3.71007371007371,
+      "grad_norm": 1.0553191900253296,
+      "learning_rate": 0.0002,
+      "loss": 0.432,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7223587223587224,
+      "grad_norm": 1.0226953029632568,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 3030
+    },
+    {
+      "epoch": 3.7346437346437344,
+      "grad_norm": 1.085554838180542,
+      "learning_rate": 0.0002,
+      "loss": 0.418,
+      "step": 3040
+    },
+    {
+      "epoch": 3.746928746928747,
+      "grad_norm": 0.9948731064796448,
+      "learning_rate": 0.0002,
+      "loss": 0.4196,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7592137592137593,
+      "grad_norm": 0.9328727126121521,
+      "learning_rate": 0.0002,
+      "loss": 0.4281,
+      "step": 3060
+    },
+    {
+      "epoch": 3.7714987714987718,
+      "grad_norm": 1.0533266067504883,
+      "learning_rate": 0.0002,
+      "loss": 0.4284,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.8213809132575989,
+      "learning_rate": 0.0002,
+      "loss": 0.4414,
+      "step": 3080
+    },
+    {
+      "epoch": 3.796068796068796,
+      "grad_norm": 0.8941594362258911,
+      "learning_rate": 0.0002,
+      "loss": 0.4348,
+      "step": 3090
+    },
+    {
+      "epoch": 3.808353808353808,
+      "grad_norm": 0.8324518203735352,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8206388206388207,
+      "grad_norm": 0.8811233639717102,
+      "learning_rate": 0.0002,
+      "loss": 0.4227,
+      "step": 3110
+    },
+    {
+      "epoch": 3.832923832923833,
+      "grad_norm": 0.8781470060348511,
+      "learning_rate": 0.0002,
+      "loss": 0.4195,
+      "step": 3120
+    },
+    {
+      "epoch": 3.845208845208845,
+      "grad_norm": 0.8994116187095642,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 3130
+    },
+    {
+      "epoch": 3.8574938574938575,
+      "grad_norm": 0.8605017066001892,
+      "learning_rate": 0.0002,
+      "loss": 0.4149,
+      "step": 3140
+    },
+    {
+      "epoch": 3.8697788697788695,
+      "grad_norm": 0.8966400027275085,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 3150
+    },
+    {
+      "epoch": 3.882063882063882,
+      "grad_norm": 0.8856554627418518,
+      "learning_rate": 0.0002,
+      "loss": 0.4245,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8943488943488944,
+      "grad_norm": 0.8971620798110962,
+      "learning_rate": 0.0002,
+      "loss": 0.4101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.906633906633907,
+      "grad_norm": 0.9807813167572021,
+      "learning_rate": 0.0002,
+      "loss": 0.3993,
+      "step": 3180
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.8614121675491333,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9312039312039313,
+      "grad_norm": 0.989171028137207,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9434889434889433,
+      "grad_norm": 0.8168872594833374,
+      "learning_rate": 0.0002,
+      "loss": 0.4182,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9557739557739557,
+      "grad_norm": 0.8109386563301086,
+      "learning_rate": 0.0002,
+      "loss": 0.4112,
+      "step": 3220
+    },
+    {
+      "epoch": 3.968058968058968,
+      "grad_norm": 1.0175853967666626,
+      "learning_rate": 0.0002,
+      "loss": 0.4165,
+      "step": 3230
+    },
+    {
+      "epoch": 3.98034398034398,
+      "grad_norm": 0.936143159866333,
+      "learning_rate": 0.0002,
+      "loss": 0.4146,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9926289926289926,
+      "grad_norm": 0.9557915925979614,
+      "learning_rate": 0.0002,
+      "loss": 0.4163,
+      "step": 3250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4401616156101227,
+      "eval_runtime": 20.8047,
+      "eval_samples_per_second": 15.91,
+      "eval_steps_per_second": 2.019,
+      "step": 3256
+    },
+    {
+      "epoch": 4.004914004914005,
+      "grad_norm": 0.7590614557266235,
+      "learning_rate": 0.0002,
+      "loss": 0.408,
+      "step": 3260
+    },
+    {
+      "epoch": 4.017199017199017,
+      "grad_norm": 0.8920791149139404,
+      "learning_rate": 0.0002,
+      "loss": 0.4001,
+      "step": 3270
+    },
+    {
+      "epoch": 4.0294840294840295,
+      "grad_norm": 0.8640421628952026,
+      "learning_rate": 0.0002,
+      "loss": 0.3789,
+      "step": 3280
+    },
+    {
+      "epoch": 4.041769041769042,
+      "grad_norm": 0.9074113965034485,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3290
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 1.0600885152816772,
+      "learning_rate": 0.0002,
+      "loss": 0.3728,
+      "step": 3300
+    },
+    {
+      "epoch": 4.066339066339066,
+      "grad_norm": 0.9682773351669312,
+      "learning_rate": 0.0002,
+      "loss": 0.3857,
+      "step": 3310
+    },
+    {
+      "epoch": 4.078624078624078,
+      "grad_norm": 0.9326395392417908,
+      "learning_rate": 0.0002,
+      "loss": 0.4007,
+      "step": 3320
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.8886597156524658,
+      "learning_rate": 0.0002,
+      "loss": 0.3823,
+      "step": 3330
+    },
+    {
+      "epoch": 4.103194103194103,
+      "grad_norm": 1.032205581665039,
+      "learning_rate": 0.0002,
+      "loss": 0.3929,
+      "step": 3340
+    },
+    {
+      "epoch": 4.115479115479116,
+      "grad_norm": 0.8669408559799194,
+      "learning_rate": 0.0002,
+      "loss": 0.3836,
+      "step": 3350
+    },
+    {
+      "epoch": 4.127764127764128,
+      "grad_norm": 0.8250347971916199,
+      "learning_rate": 0.0002,
+      "loss": 0.3866,
+      "step": 3360
+    },
+    {
+      "epoch": 4.14004914004914,
+      "grad_norm": 0.7919842600822449,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3370
+    },
+    {
+      "epoch": 4.152334152334152,
+      "grad_norm": 1.045682430267334,
+      "learning_rate": 0.0002,
+      "loss": 0.3838,
+      "step": 3380
+    },
+    {
+      "epoch": 4.164619164619165,
+      "grad_norm": 0.6873571276664734,
+      "learning_rate": 0.0002,
+      "loss": 0.3796,
+      "step": 3390
+    },
+    {
+      "epoch": 4.176904176904177,
+      "grad_norm": 1.0227675437927246,
+      "learning_rate": 0.0002,
+      "loss": 0.3942,
+      "step": 3400
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 0.9167711734771729,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 3410
+    },
+    {
+      "epoch": 4.201474201474202,
+      "grad_norm": 1.0598796606063843,
+      "learning_rate": 0.0002,
+      "loss": 0.3792,
+      "step": 3420
+    },
+    {
+      "epoch": 4.2137592137592135,
+      "grad_norm": 0.8581843972206116,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3430
+    },
+    {
+      "epoch": 4.226044226044226,
+      "grad_norm": 0.8862360119819641,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3440
+    },
+    {
+      "epoch": 4.238329238329238,
+      "grad_norm": 1.0248323678970337,
+      "learning_rate": 0.0002,
+      "loss": 0.3889,
+      "step": 3450
+    },
+    {
+      "epoch": 4.250614250614251,
+      "grad_norm": 0.8746261596679688,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3460
+    },
+    {
+      "epoch": 4.262899262899263,
+      "grad_norm": 0.7442536354064941,
+      "learning_rate": 0.0002,
+      "loss": 0.3949,
+      "step": 3470
+    },
+    {
+      "epoch": 4.275184275184275,
+      "grad_norm": 0.8295119404792786,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3480
+    },
+    {
+      "epoch": 4.287469287469287,
+      "grad_norm": 1.0634245872497559,
+      "learning_rate": 0.0002,
+      "loss": 0.3895,
+      "step": 3490
+    },
+    {
+      "epoch": 4.2997542997543,
+      "grad_norm": 0.9554621577262878,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3500
+    },
+    {
+      "epoch": 4.312039312039312,
+      "grad_norm": 1.0191723108291626,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3510
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.8573611378669739,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 3520
+    },
+    {
+      "epoch": 4.336609336609337,
+      "grad_norm": 0.9082390069961548,
+      "learning_rate": 0.0002,
+      "loss": 0.3869,
+      "step": 3530
+    },
+    {
+      "epoch": 4.348894348894349,
+      "grad_norm": 0.8650212287902832,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3540
+    },
+    {
+      "epoch": 4.361179361179361,
+      "grad_norm": 0.7186297178268433,
+      "learning_rate": 0.0002,
+      "loss": 0.3915,
+      "step": 3550
+    },
+    {
+      "epoch": 4.3734643734643734,
+      "grad_norm": 0.9750986695289612,
+      "learning_rate": 0.0002,
+      "loss": 0.3861,
+      "step": 3560
+    },
+    {
+      "epoch": 4.385749385749386,
+      "grad_norm": 1.0710467100143433,
+      "learning_rate": 0.0002,
+      "loss": 0.3967,
+      "step": 3570
+    },
+    {
+      "epoch": 4.398034398034398,
+      "grad_norm": 0.7974869012832642,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3580
+    },
+    {
+      "epoch": 4.41031941031941,
+      "grad_norm": 0.9405913949012756,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3590
+    },
+    {
+      "epoch": 4.422604422604422,
+      "grad_norm": 0.9393602609634399,
+      "learning_rate": 0.0002,
+      "loss": 0.3982,
+      "step": 3600
+    },
+    {
+      "epoch": 4.434889434889435,
+      "grad_norm": 1.0798007249832153,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 3610
+    },
+    {
+      "epoch": 4.447174447174447,
+      "grad_norm": 0.9226186275482178,
+      "learning_rate": 0.0002,
+      "loss": 0.3682,
+      "step": 3620
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 1.1046524047851562,
+      "learning_rate": 0.0002,
+      "loss": 0.3742,
+      "step": 3630
+    },
+    {
+      "epoch": 4.471744471744472,
+      "grad_norm": 0.8848567605018616,
+      "learning_rate": 0.0002,
+      "loss": 0.3886,
+      "step": 3640
+    },
+    {
+      "epoch": 4.484029484029484,
+      "grad_norm": 0.8913224339485168,
+      "learning_rate": 0.0002,
+      "loss": 0.3848,
+      "step": 3650
+    },
+    {
+      "epoch": 4.496314496314496,
+      "grad_norm": 0.8497583270072937,
+      "learning_rate": 0.0002,
+      "loss": 0.3731,
+      "step": 3660
+    },
+    {
+      "epoch": 4.5085995085995085,
+      "grad_norm": 0.8263831734657288,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 3670
+    },
+    {
+      "epoch": 4.520884520884521,
+      "grad_norm": 0.8470269441604614,
+      "learning_rate": 0.0002,
+      "loss": 0.3815,
+      "step": 3680
+    },
+    {
+      "epoch": 4.533169533169533,
+      "grad_norm": 0.860038161277771,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3690
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.8898552656173706,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3700
+    },
+    {
+      "epoch": 4.557739557739557,
+      "grad_norm": 0.8152070641517639,
+      "learning_rate": 0.0002,
+      "loss": 0.3776,
+      "step": 3710
+    },
+    {
+      "epoch": 4.57002457002457,
+      "grad_norm": 0.7847675085067749,
+      "learning_rate": 0.0002,
+      "loss": 0.383,
+      "step": 3720
+    },
+    {
+      "epoch": 4.582309582309582,
+      "grad_norm": 0.9625533819198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3730
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.9097456336021423,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 3740
+    },
+    {
+      "epoch": 4.606879606879607,
+      "grad_norm": 0.871329128742218,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 3750
+    },
+    {
+      "epoch": 4.61916461916462,
+      "grad_norm": 0.9879975914955139,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 3760
+    },
+    {
+      "epoch": 4.631449631449631,
+      "grad_norm": 0.8636731505393982,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3770
+    },
+    {
+      "epoch": 4.643734643734644,
+      "grad_norm": 1.0488964319229126,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 3780
+    },
+    {
+      "epoch": 4.656019656019656,
+      "grad_norm": 0.7637056112289429,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3790
+    },
+    {
+      "epoch": 4.6683046683046685,
+      "grad_norm": 0.8507546186447144,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 3800
+    },
+    {
+      "epoch": 4.680589680589681,
+      "grad_norm": 1.0216856002807617,
+      "learning_rate": 0.0002,
+      "loss": 0.3852,
+      "step": 3810
+    },
+    {
+      "epoch": 4.6928746928746925,
+      "grad_norm": 1.026343822479248,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 3820
+    },
+    {
+      "epoch": 4.705159705159705,
+      "grad_norm": 0.8311620950698853,
+      "learning_rate": 0.0002,
+      "loss": 0.3687,
+      "step": 3830
+    },
+    {
+      "epoch": 4.717444717444717,
+      "grad_norm": 0.7770653367042542,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 3840
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 0.7616215348243713,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3850
+    },
+    {
+      "epoch": 4.742014742014742,
+      "grad_norm": 1.0377072095870972,
+      "learning_rate": 0.0002,
+      "loss": 0.3927,
+      "step": 3860
+    },
+    {
+      "epoch": 4.754299754299755,
+      "grad_norm": 0.9713505506515503,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 3870
+    },
+    {
+      "epoch": 4.766584766584766,
+      "grad_norm": 0.8803321719169617,
+      "learning_rate": 0.0002,
+      "loss": 0.3722,
+      "step": 3880
+    },
+    {
+      "epoch": 4.778869778869779,
+      "grad_norm": 0.885535478591919,
+      "learning_rate": 0.0002,
+      "loss": 0.3756,
+      "step": 3890
+    },
+    {
+      "epoch": 4.791154791154791,
+      "grad_norm": 1.0877983570098877,
+      "learning_rate": 0.0002,
+      "loss": 0.3714,
+      "step": 3900
+    },
+    {
+      "epoch": 4.803439803439804,
+      "grad_norm": 0.7875366806983948,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3910
+    },
+    {
+      "epoch": 4.815724815724816,
+      "grad_norm": 0.8550102114677429,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 3920
+    },
+    {
+      "epoch": 4.828009828009828,
+      "grad_norm": 1.0217846632003784,
+      "learning_rate": 0.0002,
+      "loss": 0.3716,
+      "step": 3930
+    },
+    {
+      "epoch": 4.84029484029484,
+      "grad_norm": 0.7315713167190552,
+      "learning_rate": 0.0002,
+      "loss": 0.3649,
+      "step": 3940
+    },
+    {
+      "epoch": 4.8525798525798525,
+      "grad_norm": 0.8924923539161682,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3950
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 0.9730218052864075,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 3960
+    },
+    {
+      "epoch": 4.877149877149877,
+      "grad_norm": 0.9202003479003906,
+      "learning_rate": 0.0002,
+      "loss": 0.3705,
+      "step": 3970
+    },
+    {
+      "epoch": 4.88943488943489,
+      "grad_norm": 0.8173081874847412,
+      "learning_rate": 0.0002,
+      "loss": 0.3617,
+      "step": 3980
+    },
+    {
+      "epoch": 4.901719901719901,
+      "grad_norm": 0.7178564667701721,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3990
+    },
+    {
+      "epoch": 4.914004914004914,
+      "grad_norm": 0.913684606552124,
+      "learning_rate": 0.0002,
+      "loss": 0.3768,
+      "step": 4000
+    },
+    {
+      "epoch": 4.926289926289926,
+      "grad_norm": 0.8817896842956543,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 4010
+    },
+    {
+      "epoch": 4.938574938574939,
+      "grad_norm": 0.7652186751365662,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 4020
+    },
+    {
+      "epoch": 4.950859950859951,
+      "grad_norm": 0.8828630447387695,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 4030
+    },
+    {
+      "epoch": 4.963144963144963,
+      "grad_norm": 1.0878605842590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3672,
+      "step": 4040
+    },
+    {
+      "epoch": 4.975429975429975,
+      "grad_norm": 1.0845288038253784,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 4050
+    },
+    {
+      "epoch": 4.987714987714988,
+      "grad_norm": 0.8431115746498108,
+      "learning_rate": 0.0002,
+      "loss": 0.365,
+      "step": 4060
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8320387601852417,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4070
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.4017423093318939,
+      "eval_runtime": 20.8466,
+      "eval_samples_per_second": 15.878,
+      "eval_steps_per_second": 2.015,
+      "step": 4070
+    },
+    {
+      "epoch": 5.012285012285012,
+      "grad_norm": 0.8639023900032043,
+      "learning_rate": 0.0002,
+      "loss": 0.3425,
+      "step": 4080
+    },
+    {
+      "epoch": 5.024570024570025,
+      "grad_norm": 0.7123713493347168,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 4090
+    },
+    {
+      "epoch": 5.036855036855036,
+      "grad_norm": 0.9886922836303711,
+      "learning_rate": 0.0002,
+      "loss": 0.3404,
+      "step": 4100
+    },
+    {
+      "epoch": 5.049140049140049,
+      "grad_norm": 0.7880306243896484,
+      "learning_rate": 0.0002,
+      "loss": 0.3529,
+      "step": 4110
+    },
+    {
+      "epoch": 5.061425061425061,
+      "grad_norm": 0.7488741874694824,
+      "learning_rate": 0.0002,
+      "loss": 0.3406,
+      "step": 4120
+    },
+    {
+      "epoch": 5.073710073710074,
+      "grad_norm": 0.9359086751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.3542,
+      "step": 4130
+    },
+    {
+      "epoch": 5.085995085995086,
+      "grad_norm": 0.9401527047157288,
+      "learning_rate": 0.0002,
+      "loss": 0.3471,
+      "step": 4140
+    },
+    {
+      "epoch": 5.098280098280099,
+      "grad_norm": 0.8396275043487549,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 4150
+    },
+    {
+      "epoch": 5.11056511056511,
+      "grad_norm": 0.7132664918899536,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4160
+    },
+    {
+      "epoch": 5.122850122850123,
+      "grad_norm": 0.843708872795105,
+      "learning_rate": 0.0002,
+      "loss": 0.3457,
+      "step": 4170
+    },
+    {
+      "epoch": 5.135135135135135,
+      "grad_norm": 0.8733304738998413,
+      "learning_rate": 0.0002,
+      "loss": 0.3399,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1474201474201475,
+      "grad_norm": 0.9064375162124634,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4190
+    },
+    {
+      "epoch": 5.15970515970516,
+      "grad_norm": 0.900770902633667,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4200
+    },
+    {
+      "epoch": 5.171990171990172,
+      "grad_norm": 0.863853394985199,
+      "learning_rate": 0.0002,
+      "loss": 0.3475,
+      "step": 4210
+    },
+    {
+      "epoch": 5.184275184275184,
+      "grad_norm": 0.767134964466095,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 4220
+    },
+    {
+      "epoch": 5.196560196560196,
+      "grad_norm": 0.7518735527992249,
+      "learning_rate": 0.0002,
+      "loss": 0.3527,
+      "step": 4230
+    },
+    {
+      "epoch": 5.208845208845209,
+      "grad_norm": 0.8040947914123535,
+      "learning_rate": 0.0002,
+      "loss": 0.3369,
+      "step": 4240
+    },
+    {
+      "epoch": 5.221130221130221,
+      "grad_norm": 0.7827144265174866,
+      "learning_rate": 0.0002,
+      "loss": 0.3496,
+      "step": 4250
+    },
+    {
+      "epoch": 5.233415233415234,
+      "grad_norm": 0.7306333184242249,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4260
+    },
+    {
+      "epoch": 5.245700245700245,
+      "grad_norm": 1.0963380336761475,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4270
+    },
+    {
+      "epoch": 5.257985257985258,
+      "grad_norm": 0.8200454711914062,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4280
+    },
+    {
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.8666796684265137,
+      "learning_rate": 0.0002,
+      "loss": 0.3509,
+      "step": 4290
+    },
+    {
+      "epoch": 5.282555282555283,
+      "grad_norm": 0.7862894535064697,
+      "learning_rate": 0.0002,
+      "loss": 0.3423,
+      "step": 4300
+    },
+    {
+      "epoch": 5.294840294840295,
+      "grad_norm": 0.8163095712661743,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4310
+    },
+    {
+      "epoch": 5.3071253071253075,
+      "grad_norm": 0.8069050908088684,
+      "learning_rate": 0.0002,
+      "loss": 0.34,
+      "step": 4320
+    },
+    {
+      "epoch": 5.319410319410319,
+      "grad_norm": 0.7858486175537109,
+      "learning_rate": 0.0002,
+      "loss": 0.3532,
+      "step": 4330
+    },
+    {
+      "epoch": 5.3316953316953315,
+      "grad_norm": 0.950339674949646,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4340
+    },
+    {
+      "epoch": 5.343980343980344,
+      "grad_norm": 0.9056477546691895,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4350
+    },
+    {
+      "epoch": 5.356265356265356,
+      "grad_norm": 0.9619399905204773,
+      "learning_rate": 0.0002,
+      "loss": 0.3538,
+      "step": 4360
+    },
+    {
+      "epoch": 5.368550368550369,
+      "grad_norm": 0.9778652191162109,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4370
+    },
+    {
+      "epoch": 5.38083538083538,
+      "grad_norm": 0.6919555068016052,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4380
+    },
+    {
+      "epoch": 5.393120393120393,
+      "grad_norm": 0.8121668696403503,
+      "learning_rate": 0.0002,
+      "loss": 0.3426,
+      "step": 4390
+    },
+    {
+      "epoch": 5.405405405405405,
+      "grad_norm": 0.8481289148330688,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4400
+    },
+    {
+      "epoch": 5.417690417690418,
+      "grad_norm": 0.8727408647537231,
+      "learning_rate": 0.0002,
+      "loss": 0.345,
+      "step": 4410
+    },
+    {
+      "epoch": 5.42997542997543,
+      "grad_norm": 0.8920271396636963,
+      "learning_rate": 0.0002,
+      "loss": 0.3554,
+      "step": 4420
+    },
+    {
+      "epoch": 5.442260442260443,
+      "grad_norm": 0.7758749723434448,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4430
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.8847506642341614,
+      "learning_rate": 0.0002,
+      "loss": 0.3483,
+      "step": 4440
+    },
+    {
+      "epoch": 5.466830466830467,
+      "grad_norm": 0.9760470390319824,
+      "learning_rate": 0.0002,
+      "loss": 0.3557,
+      "step": 4450
+    },
+    {
+      "epoch": 5.479115479115479,
+      "grad_norm": 0.8940271139144897,
+      "learning_rate": 0.0002,
+      "loss": 0.3536,
+      "step": 4460
+    },
+    {
+      "epoch": 5.4914004914004915,
+      "grad_norm": 0.8668502569198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 4470
+    },
+    {
+      "epoch": 5.503685503685504,
+      "grad_norm": 0.9097439050674438,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4480
+    },
+    {
+      "epoch": 5.515970515970516,
+      "grad_norm": 0.8217208981513977,
+      "learning_rate": 0.0002,
+      "loss": 0.3417,
+      "step": 4490
+    },
+    {
+      "epoch": 5.528255528255528,
+      "grad_norm": 0.7853189706802368,
+      "learning_rate": 0.0002,
+      "loss": 0.3482,
+      "step": 4500
+    },
+    {
+      "epoch": 5.54054054054054,
+      "grad_norm": 1.1113477945327759,
+      "learning_rate": 0.0002,
+      "loss": 0.3479,
+      "step": 4510
+    },
+    {
+      "epoch": 5.552825552825553,
+      "grad_norm": 0.8637538552284241,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4520
+    },
+    {
+      "epoch": 5.565110565110565,
+      "grad_norm": 1.0230066776275635,
+      "learning_rate": 0.0002,
+      "loss": 0.3403,
+      "step": 4530
+    },
+    {
+      "epoch": 5.577395577395578,
+      "grad_norm": 0.8972793817520142,
+      "learning_rate": 0.0002,
+      "loss": 0.3588,
+      "step": 4540
+    },
+    {
+      "epoch": 5.58968058968059,
+      "grad_norm": 0.7950642704963684,
+      "learning_rate": 0.0002,
+      "loss": 0.3428,
+      "step": 4550
+    },
+    {
+      "epoch": 5.601965601965602,
+      "grad_norm": 1.113753318786621,
+      "learning_rate": 0.0002,
+      "loss": 0.3468,
+      "step": 4560
+    },
+    {
+      "epoch": 5.614250614250614,
+      "grad_norm": 0.7842669486999512,
+      "learning_rate": 0.0002,
+      "loss": 0.3354,
+      "step": 4570
+    },
+    {
+      "epoch": 5.6265356265356266,
+      "grad_norm": 0.9713512063026428,
+      "learning_rate": 0.0002,
+      "loss": 0.3419,
+      "step": 4580
+    },
+    {
+      "epoch": 5.638820638820639,
+      "grad_norm": 0.9451650977134705,
+      "learning_rate": 0.0002,
+      "loss": 0.3502,
+      "step": 4590
+    },
+    {
+      "epoch": 5.651105651105651,
+      "grad_norm": 1.055484414100647,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4600
+    },
+    {
+      "epoch": 5.663390663390663,
+      "grad_norm": 0.8408507704734802,
+      "learning_rate": 0.0002,
+      "loss": 0.3436,
+      "step": 4610
+    },
+    {
+      "epoch": 5.675675675675675,
+      "grad_norm": 1.0293926000595093,
+      "learning_rate": 0.0002,
+      "loss": 0.3619,
+      "step": 4620
+    },
+    {
+      "epoch": 5.687960687960688,
+      "grad_norm": 0.7198245525360107,
+      "learning_rate": 0.0002,
+      "loss": 0.3484,
+      "step": 4630
+    },
+    {
+      "epoch": 5.7002457002457,
+      "grad_norm": 0.7564466595649719,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 4640
+    },
+    {
+      "epoch": 5.712530712530713,
+      "grad_norm": 0.7980002760887146,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4650
+    },
+    {
+      "epoch": 5.724815724815725,
+      "grad_norm": 0.8685088753700256,
+      "learning_rate": 0.0002,
+      "loss": 0.3478,
+      "step": 4660
+    },
+    {
+      "epoch": 5.737100737100737,
+      "grad_norm": 0.8816949129104614,
+      "learning_rate": 0.0002,
+      "loss": 0.3692,
+      "step": 4670
+    },
+    {
+      "epoch": 5.749385749385749,
+      "grad_norm": 0.7154731750488281,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4680
+    },
+    {
+      "epoch": 5.761670761670762,
+      "grad_norm": 0.9430679678916931,
+      "learning_rate": 0.0002,
+      "loss": 0.3503,
+      "step": 4690
+    },
+    {
+      "epoch": 5.773955773955774,
+      "grad_norm": 0.7640151381492615,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4700
+    },
+    {
+      "epoch": 5.7862407862407865,
+      "grad_norm": 1.0920690298080444,
+      "learning_rate": 0.0002,
+      "loss": 0.3444,
+      "step": 4710
+    },
+    {
+      "epoch": 5.798525798525798,
+      "grad_norm": 0.9362104535102844,
+      "learning_rate": 0.0002,
+      "loss": 0.3356,
+      "step": 4720
+    },
+    {
+      "epoch": 5.8108108108108105,
+      "grad_norm": 0.8392294645309448,
+      "learning_rate": 0.0002,
+      "loss": 0.339,
+      "step": 4730
+    },
+    {
+      "epoch": 5.823095823095823,
+      "grad_norm": 0.9893582463264465,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 4740
+    },
+    {
+      "epoch": 5.835380835380835,
+      "grad_norm": 0.6985510587692261,
+      "learning_rate": 0.0002,
+      "loss": 0.3446,
+      "step": 4750
+    },
+    {
+      "epoch": 5.847665847665848,
+      "grad_norm": 0.8906862735748291,
+      "learning_rate": 0.0002,
+      "loss": 0.3534,
+      "step": 4760
+    },
+    {
+      "epoch": 5.85995085995086,
+      "grad_norm": 0.8036413192749023,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 4770
+    },
+    {
+      "epoch": 5.872235872235873,
+      "grad_norm": 0.9948155283927917,
+      "learning_rate": 0.0002,
+      "loss": 0.3326,
+      "step": 4780
+    },
+    {
+      "epoch": 5.884520884520884,
+      "grad_norm": 0.8618432283401489,
+      "learning_rate": 0.0002,
+      "loss": 0.3385,
+      "step": 4790
+    },
+    {
+      "epoch": 5.896805896805897,
+      "grad_norm": 1.0422909259796143,
+      "learning_rate": 0.0002,
+      "loss": 0.3302,
+      "step": 4800
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 1.1892569065093994,
+      "learning_rate": 0.0002,
+      "loss": 0.3448,
+      "step": 4810
+    },
+    {
+      "epoch": 5.921375921375922,
+      "grad_norm": 1.1459916830062866,
+      "learning_rate": 0.0002,
+      "loss": 0.3506,
+      "step": 4820
+    },
+    {
+      "epoch": 5.933660933660933,
+      "grad_norm": 1.056235909461975,
+      "learning_rate": 0.0002,
+      "loss": 0.3387,
+      "step": 4830
+    },
+    {
+      "epoch": 5.945945945945946,
+      "grad_norm": 0.8517277240753174,
+      "learning_rate": 0.0002,
+      "loss": 0.344,
+      "step": 4840
+    },
+    {
+      "epoch": 5.958230958230958,
+      "grad_norm": 0.8153380751609802,
+      "learning_rate": 0.0002,
+      "loss": 0.3421,
+      "step": 4850
+    },
+    {
+      "epoch": 5.9705159705159705,
+      "grad_norm": 0.7907533049583435,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4860
+    },
+    {
+      "epoch": 5.982800982800983,
+      "grad_norm": 0.8443069458007812,
+      "learning_rate": 0.0002,
+      "loss": 0.3337,
+      "step": 4870
+    },
+    {
+      "epoch": 5.995085995085995,
+      "grad_norm": 0.8711344003677368,
+      "learning_rate": 0.0002,
+      "loss": 0.3351,
+      "step": 4880
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.3778059184551239,
+      "eval_runtime": 20.6858,
+      "eval_samples_per_second": 16.001,
+      "eval_steps_per_second": 2.03,
+      "step": 4884
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.969223010064794e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bbbac78111bbbebee8bd59f069df28eae1d558eb
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac100f45a0c499add65357c09818dd6d6facc45332df9c690ab5f0ea75b7ca5f
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c514b4857d536d6dbb6f6c6a1a6aeca2dbbd2c56
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44697f15165884ed87cc7c2f9a1856f13b076d9841d5d132b9ccec5c555f65e7
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..184c86fd018ad198f1d67c1e0e9dfa3593fc3856
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e363cf2a25a5afacf998f3c2bdefd67fef7ceac03284ee2232e8d6ea3bf8af5
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eefe24e13423ad1b109be1301438e1c95a1b4427
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a03df00df238c3a31bf602f5e2bbbee686d5176e795f07fdbbed25e7e6b01ca
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e11ba2d077be714be514fcb203c720357accabc8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/trainer_state.json
@@ -0,0 +1,4072 @@
+{
+  "best_metric": 0.3616626560688019,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698",
+  "epoch": 7.0,
+  "eval_steps": 10,
+  "global_step": 5698,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    },
+    {
+      "epoch": 3.0098280098280097,
+      "grad_norm": 0.7644656896591187,
+      "learning_rate": 0.0002,
+      "loss": 0.4362,
+      "step": 2450
+    },
+    {
+      "epoch": 3.022113022113022,
+      "grad_norm": 0.9077525734901428,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0343980343980346,
+      "grad_norm": 0.7859287261962891,
+      "learning_rate": 0.0002,
+      "loss": 0.422,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0466830466830466,
+      "grad_norm": 1.1200323104858398,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 2480
+    },
+    {
+      "epoch": 3.058968058968059,
+      "grad_norm": 0.7570453882217407,
+      "learning_rate": 0.0002,
+      "loss": 0.4519,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0712530712530715,
+      "grad_norm": 0.9450915455818176,
+      "learning_rate": 0.0002,
+      "loss": 0.4351,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0835380835380835,
+      "grad_norm": 0.8303545117378235,
+      "learning_rate": 0.0002,
+      "loss": 0.4343,
+      "step": 2510
+    },
+    {
+      "epoch": 3.095823095823096,
+      "grad_norm": 0.8864443898200989,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2520
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.945324718952179,
+      "learning_rate": 0.0002,
+      "loss": 0.4601,
+      "step": 2530
+    },
+    {
+      "epoch": 3.1203931203931203,
+      "grad_norm": 1.0562494993209839,
+      "learning_rate": 0.0002,
+      "loss": 0.4345,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1326781326781328,
+      "grad_norm": 0.8607500195503235,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1449631449631448,
+      "grad_norm": 0.8719640374183655,
+      "learning_rate": 0.0002,
+      "loss": 0.456,
+      "step": 2560
+    },
+    {
+      "epoch": 3.157248157248157,
+      "grad_norm": 0.8647059202194214,
+      "learning_rate": 0.0002,
+      "loss": 0.4469,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1695331695331697,
+      "grad_norm": 0.8346507549285889,
+      "learning_rate": 0.0002,
+      "loss": 0.4483,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 1.0208854675292969,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 2590
+    },
+    {
+      "epoch": 3.194103194103194,
+      "grad_norm": 0.7064385414123535,
+      "learning_rate": 0.0002,
+      "loss": 0.435,
+      "step": 2600
+    },
+    {
+      "epoch": 3.2063882063882065,
+      "grad_norm": 0.927347719669342,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2186732186732185,
+      "grad_norm": 0.943517804145813,
+      "learning_rate": 0.0002,
+      "loss": 0.4561,
+      "step": 2620
+    },
+    {
+      "epoch": 3.230958230958231,
+      "grad_norm": 0.7837198376655579,
+      "learning_rate": 0.0002,
+      "loss": 0.4225,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.7752765417098999,
+      "learning_rate": 0.0002,
+      "loss": 0.4494,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2555282555282554,
+      "grad_norm": 0.8578953146934509,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2650
+    },
+    {
+      "epoch": 3.267813267813268,
+      "grad_norm": 1.0209529399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2800982800982803,
+      "grad_norm": 0.9069030284881592,
+      "learning_rate": 0.0002,
+      "loss": 0.4517,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2923832923832923,
+      "grad_norm": 0.8454729318618774,
+      "learning_rate": 0.0002,
+      "loss": 0.4262,
+      "step": 2680
+    },
+    {
+      "epoch": 3.3046683046683047,
+      "grad_norm": 0.8253099322319031,
+      "learning_rate": 0.0002,
+      "loss": 0.4349,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3169533169533167,
+      "grad_norm": 0.8765934109687805,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 2700
+    },
+    {
+      "epoch": 3.329238329238329,
+      "grad_norm": 0.8149126172065735,
+      "learning_rate": 0.0002,
+      "loss": 0.4518,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3415233415233416,
+      "grad_norm": 0.8820102214813232,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3538083538083536,
+      "grad_norm": 0.8813952803611755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 2730
+    },
+    {
+      "epoch": 3.366093366093366,
+      "grad_norm": 1.0338447093963623,
+      "learning_rate": 0.0002,
+      "loss": 0.4396,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8780209422111511,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2750
+    },
+    {
+      "epoch": 3.3906633906633905,
+      "grad_norm": 0.9017151594161987,
+      "learning_rate": 0.0002,
+      "loss": 0.441,
+      "step": 2760
+    },
+    {
+      "epoch": 3.402948402948403,
+      "grad_norm": 0.8647638559341431,
+      "learning_rate": 0.0002,
+      "loss": 0.446,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4152334152334154,
+      "grad_norm": 0.8298183679580688,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4275184275184274,
+      "grad_norm": 0.9298108816146851,
+      "learning_rate": 0.0002,
+      "loss": 0.4406,
+      "step": 2790
+    },
+    {
+      "epoch": 3.43980343980344,
+      "grad_norm": 0.8909980058670044,
+      "learning_rate": 0.0002,
+      "loss": 0.4145,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4520884520884523,
+      "grad_norm": 0.8027496933937073,
+      "learning_rate": 0.0002,
+      "loss": 0.4148,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4643734643734643,
+      "grad_norm": 0.8766195774078369,
+      "learning_rate": 0.0002,
+      "loss": 0.4244,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4766584766584767,
+      "grad_norm": 0.8194443583488464,
+      "learning_rate": 0.0002,
+      "loss": 0.4292,
+      "step": 2830
+    },
+    {
+      "epoch": 3.488943488943489,
+      "grad_norm": 0.9862873554229736,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 2840
+    },
+    {
+      "epoch": 3.501228501228501,
+      "grad_norm": 0.8755377531051636,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.7300266027450562,
+      "learning_rate": 0.0002,
+      "loss": 0.4231,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5257985257985256,
+      "grad_norm": 0.8342461585998535,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 2870
+    },
+    {
+      "epoch": 3.538083538083538,
+      "grad_norm": 0.8624151349067688,
+      "learning_rate": 0.0002,
+      "loss": 0.4395,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5503685503685505,
+      "grad_norm": 0.8931261301040649,
+      "learning_rate": 0.0002,
+      "loss": 0.4064,
+      "step": 2890
+    },
+    {
+      "epoch": 3.562653562653563,
+      "grad_norm": 0.8617086410522461,
+      "learning_rate": 0.0002,
+      "loss": 0.4358,
+      "step": 2900
+    },
+    {
+      "epoch": 3.574938574938575,
+      "grad_norm": 0.8754099607467651,
+      "learning_rate": 0.0002,
+      "loss": 0.419,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5872235872235874,
+      "grad_norm": 0.8345834612846375,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5995085995085994,
+      "grad_norm": 1.1414062976837158,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2930
+    },
+    {
+      "epoch": 3.611793611793612,
+      "grad_norm": 0.994860053062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4297,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6240786240786242,
+      "grad_norm": 1.19268000125885,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.8399543762207031,
+      "learning_rate": 0.0002,
+      "loss": 0.4029,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.9873217940330505,
+      "learning_rate": 0.0002,
+      "loss": 0.4432,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6609336609336607,
+      "grad_norm": 0.9116013646125793,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2980
+    },
+    {
+      "epoch": 3.673218673218673,
+      "grad_norm": 0.9503833651542664,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6855036855036856,
+      "grad_norm": 0.9401112794876099,
+      "learning_rate": 0.0002,
+      "loss": 0.4306,
+      "step": 3000
+    },
+    {
+      "epoch": 3.697788697788698,
+      "grad_norm": 1.00745689868927,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 3010
+    },
+    {
+      "epoch": 3.71007371007371,
+      "grad_norm": 1.0553191900253296,
+      "learning_rate": 0.0002,
+      "loss": 0.432,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7223587223587224,
+      "grad_norm": 1.0226953029632568,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 3030
+    },
+    {
+      "epoch": 3.7346437346437344,
+      "grad_norm": 1.085554838180542,
+      "learning_rate": 0.0002,
+      "loss": 0.418,
+      "step": 3040
+    },
+    {
+      "epoch": 3.746928746928747,
+      "grad_norm": 0.9948731064796448,
+      "learning_rate": 0.0002,
+      "loss": 0.4196,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7592137592137593,
+      "grad_norm": 0.9328727126121521,
+      "learning_rate": 0.0002,
+      "loss": 0.4281,
+      "step": 3060
+    },
+    {
+      "epoch": 3.7714987714987718,
+      "grad_norm": 1.0533266067504883,
+      "learning_rate": 0.0002,
+      "loss": 0.4284,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.8213809132575989,
+      "learning_rate": 0.0002,
+      "loss": 0.4414,
+      "step": 3080
+    },
+    {
+      "epoch": 3.796068796068796,
+      "grad_norm": 0.8941594362258911,
+      "learning_rate": 0.0002,
+      "loss": 0.4348,
+      "step": 3090
+    },
+    {
+      "epoch": 3.808353808353808,
+      "grad_norm": 0.8324518203735352,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8206388206388207,
+      "grad_norm": 0.8811233639717102,
+      "learning_rate": 0.0002,
+      "loss": 0.4227,
+      "step": 3110
+    },
+    {
+      "epoch": 3.832923832923833,
+      "grad_norm": 0.8781470060348511,
+      "learning_rate": 0.0002,
+      "loss": 0.4195,
+      "step": 3120
+    },
+    {
+      "epoch": 3.845208845208845,
+      "grad_norm": 0.8994116187095642,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 3130
+    },
+    {
+      "epoch": 3.8574938574938575,
+      "grad_norm": 0.8605017066001892,
+      "learning_rate": 0.0002,
+      "loss": 0.4149,
+      "step": 3140
+    },
+    {
+      "epoch": 3.8697788697788695,
+      "grad_norm": 0.8966400027275085,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 3150
+    },
+    {
+      "epoch": 3.882063882063882,
+      "grad_norm": 0.8856554627418518,
+      "learning_rate": 0.0002,
+      "loss": 0.4245,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8943488943488944,
+      "grad_norm": 0.8971620798110962,
+      "learning_rate": 0.0002,
+      "loss": 0.4101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.906633906633907,
+      "grad_norm": 0.9807813167572021,
+      "learning_rate": 0.0002,
+      "loss": 0.3993,
+      "step": 3180
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.8614121675491333,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9312039312039313,
+      "grad_norm": 0.989171028137207,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9434889434889433,
+      "grad_norm": 0.8168872594833374,
+      "learning_rate": 0.0002,
+      "loss": 0.4182,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9557739557739557,
+      "grad_norm": 0.8109386563301086,
+      "learning_rate": 0.0002,
+      "loss": 0.4112,
+      "step": 3220
+    },
+    {
+      "epoch": 3.968058968058968,
+      "grad_norm": 1.0175853967666626,
+      "learning_rate": 0.0002,
+      "loss": 0.4165,
+      "step": 3230
+    },
+    {
+      "epoch": 3.98034398034398,
+      "grad_norm": 0.936143159866333,
+      "learning_rate": 0.0002,
+      "loss": 0.4146,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9926289926289926,
+      "grad_norm": 0.9557915925979614,
+      "learning_rate": 0.0002,
+      "loss": 0.4163,
+      "step": 3250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4401616156101227,
+      "eval_runtime": 20.8047,
+      "eval_samples_per_second": 15.91,
+      "eval_steps_per_second": 2.019,
+      "step": 3256
+    },
+    {
+      "epoch": 4.004914004914005,
+      "grad_norm": 0.7590614557266235,
+      "learning_rate": 0.0002,
+      "loss": 0.408,
+      "step": 3260
+    },
+    {
+      "epoch": 4.017199017199017,
+      "grad_norm": 0.8920791149139404,
+      "learning_rate": 0.0002,
+      "loss": 0.4001,
+      "step": 3270
+    },
+    {
+      "epoch": 4.0294840294840295,
+      "grad_norm": 0.8640421628952026,
+      "learning_rate": 0.0002,
+      "loss": 0.3789,
+      "step": 3280
+    },
+    {
+      "epoch": 4.041769041769042,
+      "grad_norm": 0.9074113965034485,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3290
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 1.0600885152816772,
+      "learning_rate": 0.0002,
+      "loss": 0.3728,
+      "step": 3300
+    },
+    {
+      "epoch": 4.066339066339066,
+      "grad_norm": 0.9682773351669312,
+      "learning_rate": 0.0002,
+      "loss": 0.3857,
+      "step": 3310
+    },
+    {
+      "epoch": 4.078624078624078,
+      "grad_norm": 0.9326395392417908,
+      "learning_rate": 0.0002,
+      "loss": 0.4007,
+      "step": 3320
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.8886597156524658,
+      "learning_rate": 0.0002,
+      "loss": 0.3823,
+      "step": 3330
+    },
+    {
+      "epoch": 4.103194103194103,
+      "grad_norm": 1.032205581665039,
+      "learning_rate": 0.0002,
+      "loss": 0.3929,
+      "step": 3340
+    },
+    {
+      "epoch": 4.115479115479116,
+      "grad_norm": 0.8669408559799194,
+      "learning_rate": 0.0002,
+      "loss": 0.3836,
+      "step": 3350
+    },
+    {
+      "epoch": 4.127764127764128,
+      "grad_norm": 0.8250347971916199,
+      "learning_rate": 0.0002,
+      "loss": 0.3866,
+      "step": 3360
+    },
+    {
+      "epoch": 4.14004914004914,
+      "grad_norm": 0.7919842600822449,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3370
+    },
+    {
+      "epoch": 4.152334152334152,
+      "grad_norm": 1.045682430267334,
+      "learning_rate": 0.0002,
+      "loss": 0.3838,
+      "step": 3380
+    },
+    {
+      "epoch": 4.164619164619165,
+      "grad_norm": 0.6873571276664734,
+      "learning_rate": 0.0002,
+      "loss": 0.3796,
+      "step": 3390
+    },
+    {
+      "epoch": 4.176904176904177,
+      "grad_norm": 1.0227675437927246,
+      "learning_rate": 0.0002,
+      "loss": 0.3942,
+      "step": 3400
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 0.9167711734771729,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 3410
+    },
+    {
+      "epoch": 4.201474201474202,
+      "grad_norm": 1.0598796606063843,
+      "learning_rate": 0.0002,
+      "loss": 0.3792,
+      "step": 3420
+    },
+    {
+      "epoch": 4.2137592137592135,
+      "grad_norm": 0.8581843972206116,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3430
+    },
+    {
+      "epoch": 4.226044226044226,
+      "grad_norm": 0.8862360119819641,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3440
+    },
+    {
+      "epoch": 4.238329238329238,
+      "grad_norm": 1.0248323678970337,
+      "learning_rate": 0.0002,
+      "loss": 0.3889,
+      "step": 3450
+    },
+    {
+      "epoch": 4.250614250614251,
+      "grad_norm": 0.8746261596679688,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3460
+    },
+    {
+      "epoch": 4.262899262899263,
+      "grad_norm": 0.7442536354064941,
+      "learning_rate": 0.0002,
+      "loss": 0.3949,
+      "step": 3470
+    },
+    {
+      "epoch": 4.275184275184275,
+      "grad_norm": 0.8295119404792786,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3480
+    },
+    {
+      "epoch": 4.287469287469287,
+      "grad_norm": 1.0634245872497559,
+      "learning_rate": 0.0002,
+      "loss": 0.3895,
+      "step": 3490
+    },
+    {
+      "epoch": 4.2997542997543,
+      "grad_norm": 0.9554621577262878,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3500
+    },
+    {
+      "epoch": 4.312039312039312,
+      "grad_norm": 1.0191723108291626,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3510
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.8573611378669739,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 3520
+    },
+    {
+      "epoch": 4.336609336609337,
+      "grad_norm": 0.9082390069961548,
+      "learning_rate": 0.0002,
+      "loss": 0.3869,
+      "step": 3530
+    },
+    {
+      "epoch": 4.348894348894349,
+      "grad_norm": 0.8650212287902832,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3540
+    },
+    {
+      "epoch": 4.361179361179361,
+      "grad_norm": 0.7186297178268433,
+      "learning_rate": 0.0002,
+      "loss": 0.3915,
+      "step": 3550
+    },
+    {
+      "epoch": 4.3734643734643734,
+      "grad_norm": 0.9750986695289612,
+      "learning_rate": 0.0002,
+      "loss": 0.3861,
+      "step": 3560
+    },
+    {
+      "epoch": 4.385749385749386,
+      "grad_norm": 1.0710467100143433,
+      "learning_rate": 0.0002,
+      "loss": 0.3967,
+      "step": 3570
+    },
+    {
+      "epoch": 4.398034398034398,
+      "grad_norm": 0.7974869012832642,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3580
+    },
+    {
+      "epoch": 4.41031941031941,
+      "grad_norm": 0.9405913949012756,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3590
+    },
+    {
+      "epoch": 4.422604422604422,
+      "grad_norm": 0.9393602609634399,
+      "learning_rate": 0.0002,
+      "loss": 0.3982,
+      "step": 3600
+    },
+    {
+      "epoch": 4.434889434889435,
+      "grad_norm": 1.0798007249832153,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 3610
+    },
+    {
+      "epoch": 4.447174447174447,
+      "grad_norm": 0.9226186275482178,
+      "learning_rate": 0.0002,
+      "loss": 0.3682,
+      "step": 3620
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 1.1046524047851562,
+      "learning_rate": 0.0002,
+      "loss": 0.3742,
+      "step": 3630
+    },
+    {
+      "epoch": 4.471744471744472,
+      "grad_norm": 0.8848567605018616,
+      "learning_rate": 0.0002,
+      "loss": 0.3886,
+      "step": 3640
+    },
+    {
+      "epoch": 4.484029484029484,
+      "grad_norm": 0.8913224339485168,
+      "learning_rate": 0.0002,
+      "loss": 0.3848,
+      "step": 3650
+    },
+    {
+      "epoch": 4.496314496314496,
+      "grad_norm": 0.8497583270072937,
+      "learning_rate": 0.0002,
+      "loss": 0.3731,
+      "step": 3660
+    },
+    {
+      "epoch": 4.5085995085995085,
+      "grad_norm": 0.8263831734657288,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 3670
+    },
+    {
+      "epoch": 4.520884520884521,
+      "grad_norm": 0.8470269441604614,
+      "learning_rate": 0.0002,
+      "loss": 0.3815,
+      "step": 3680
+    },
+    {
+      "epoch": 4.533169533169533,
+      "grad_norm": 0.860038161277771,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3690
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.8898552656173706,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3700
+    },
+    {
+      "epoch": 4.557739557739557,
+      "grad_norm": 0.8152070641517639,
+      "learning_rate": 0.0002,
+      "loss": 0.3776,
+      "step": 3710
+    },
+    {
+      "epoch": 4.57002457002457,
+      "grad_norm": 0.7847675085067749,
+      "learning_rate": 0.0002,
+      "loss": 0.383,
+      "step": 3720
+    },
+    {
+      "epoch": 4.582309582309582,
+      "grad_norm": 0.9625533819198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3730
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.9097456336021423,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 3740
+    },
+    {
+      "epoch": 4.606879606879607,
+      "grad_norm": 0.871329128742218,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 3750
+    },
+    {
+      "epoch": 4.61916461916462,
+      "grad_norm": 0.9879975914955139,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 3760
+    },
+    {
+      "epoch": 4.631449631449631,
+      "grad_norm": 0.8636731505393982,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3770
+    },
+    {
+      "epoch": 4.643734643734644,
+      "grad_norm": 1.0488964319229126,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 3780
+    },
+    {
+      "epoch": 4.656019656019656,
+      "grad_norm": 0.7637056112289429,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3790
+    },
+    {
+      "epoch": 4.6683046683046685,
+      "grad_norm": 0.8507546186447144,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 3800
+    },
+    {
+      "epoch": 4.680589680589681,
+      "grad_norm": 1.0216856002807617,
+      "learning_rate": 0.0002,
+      "loss": 0.3852,
+      "step": 3810
+    },
+    {
+      "epoch": 4.6928746928746925,
+      "grad_norm": 1.026343822479248,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 3820
+    },
+    {
+      "epoch": 4.705159705159705,
+      "grad_norm": 0.8311620950698853,
+      "learning_rate": 0.0002,
+      "loss": 0.3687,
+      "step": 3830
+    },
+    {
+      "epoch": 4.717444717444717,
+      "grad_norm": 0.7770653367042542,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 3840
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 0.7616215348243713,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3850
+    },
+    {
+      "epoch": 4.742014742014742,
+      "grad_norm": 1.0377072095870972,
+      "learning_rate": 0.0002,
+      "loss": 0.3927,
+      "step": 3860
+    },
+    {
+      "epoch": 4.754299754299755,
+      "grad_norm": 0.9713505506515503,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 3870
+    },
+    {
+      "epoch": 4.766584766584766,
+      "grad_norm": 0.8803321719169617,
+      "learning_rate": 0.0002,
+      "loss": 0.3722,
+      "step": 3880
+    },
+    {
+      "epoch": 4.778869778869779,
+      "grad_norm": 0.885535478591919,
+      "learning_rate": 0.0002,
+      "loss": 0.3756,
+      "step": 3890
+    },
+    {
+      "epoch": 4.791154791154791,
+      "grad_norm": 1.0877983570098877,
+      "learning_rate": 0.0002,
+      "loss": 0.3714,
+      "step": 3900
+    },
+    {
+      "epoch": 4.803439803439804,
+      "grad_norm": 0.7875366806983948,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3910
+    },
+    {
+      "epoch": 4.815724815724816,
+      "grad_norm": 0.8550102114677429,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 3920
+    },
+    {
+      "epoch": 4.828009828009828,
+      "grad_norm": 1.0217846632003784,
+      "learning_rate": 0.0002,
+      "loss": 0.3716,
+      "step": 3930
+    },
+    {
+      "epoch": 4.84029484029484,
+      "grad_norm": 0.7315713167190552,
+      "learning_rate": 0.0002,
+      "loss": 0.3649,
+      "step": 3940
+    },
+    {
+      "epoch": 4.8525798525798525,
+      "grad_norm": 0.8924923539161682,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3950
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 0.9730218052864075,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 3960
+    },
+    {
+      "epoch": 4.877149877149877,
+      "grad_norm": 0.9202003479003906,
+      "learning_rate": 0.0002,
+      "loss": 0.3705,
+      "step": 3970
+    },
+    {
+      "epoch": 4.88943488943489,
+      "grad_norm": 0.8173081874847412,
+      "learning_rate": 0.0002,
+      "loss": 0.3617,
+      "step": 3980
+    },
+    {
+      "epoch": 4.901719901719901,
+      "grad_norm": 0.7178564667701721,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3990
+    },
+    {
+      "epoch": 4.914004914004914,
+      "grad_norm": 0.913684606552124,
+      "learning_rate": 0.0002,
+      "loss": 0.3768,
+      "step": 4000
+    },
+    {
+      "epoch": 4.926289926289926,
+      "grad_norm": 0.8817896842956543,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 4010
+    },
+    {
+      "epoch": 4.938574938574939,
+      "grad_norm": 0.7652186751365662,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 4020
+    },
+    {
+      "epoch": 4.950859950859951,
+      "grad_norm": 0.8828630447387695,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 4030
+    },
+    {
+      "epoch": 4.963144963144963,
+      "grad_norm": 1.0878605842590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3672,
+      "step": 4040
+    },
+    {
+      "epoch": 4.975429975429975,
+      "grad_norm": 1.0845288038253784,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 4050
+    },
+    {
+      "epoch": 4.987714987714988,
+      "grad_norm": 0.8431115746498108,
+      "learning_rate": 0.0002,
+      "loss": 0.365,
+      "step": 4060
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8320387601852417,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4070
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.4017423093318939,
+      "eval_runtime": 20.8466,
+      "eval_samples_per_second": 15.878,
+      "eval_steps_per_second": 2.015,
+      "step": 4070
+    },
+    {
+      "epoch": 5.012285012285012,
+      "grad_norm": 0.8639023900032043,
+      "learning_rate": 0.0002,
+      "loss": 0.3425,
+      "step": 4080
+    },
+    {
+      "epoch": 5.024570024570025,
+      "grad_norm": 0.7123713493347168,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 4090
+    },
+    {
+      "epoch": 5.036855036855036,
+      "grad_norm": 0.9886922836303711,
+      "learning_rate": 0.0002,
+      "loss": 0.3404,
+      "step": 4100
+    },
+    {
+      "epoch": 5.049140049140049,
+      "grad_norm": 0.7880306243896484,
+      "learning_rate": 0.0002,
+      "loss": 0.3529,
+      "step": 4110
+    },
+    {
+      "epoch": 5.061425061425061,
+      "grad_norm": 0.7488741874694824,
+      "learning_rate": 0.0002,
+      "loss": 0.3406,
+      "step": 4120
+    },
+    {
+      "epoch": 5.073710073710074,
+      "grad_norm": 0.9359086751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.3542,
+      "step": 4130
+    },
+    {
+      "epoch": 5.085995085995086,
+      "grad_norm": 0.9401527047157288,
+      "learning_rate": 0.0002,
+      "loss": 0.3471,
+      "step": 4140
+    },
+    {
+      "epoch": 5.098280098280099,
+      "grad_norm": 0.8396275043487549,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 4150
+    },
+    {
+      "epoch": 5.11056511056511,
+      "grad_norm": 0.7132664918899536,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4160
+    },
+    {
+      "epoch": 5.122850122850123,
+      "grad_norm": 0.843708872795105,
+      "learning_rate": 0.0002,
+      "loss": 0.3457,
+      "step": 4170
+    },
+    {
+      "epoch": 5.135135135135135,
+      "grad_norm": 0.8733304738998413,
+      "learning_rate": 0.0002,
+      "loss": 0.3399,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1474201474201475,
+      "grad_norm": 0.9064375162124634,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4190
+    },
+    {
+      "epoch": 5.15970515970516,
+      "grad_norm": 0.900770902633667,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4200
+    },
+    {
+      "epoch": 5.171990171990172,
+      "grad_norm": 0.863853394985199,
+      "learning_rate": 0.0002,
+      "loss": 0.3475,
+      "step": 4210
+    },
+    {
+      "epoch": 5.184275184275184,
+      "grad_norm": 0.767134964466095,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 4220
+    },
+    {
+      "epoch": 5.196560196560196,
+      "grad_norm": 0.7518735527992249,
+      "learning_rate": 0.0002,
+      "loss": 0.3527,
+      "step": 4230
+    },
+    {
+      "epoch": 5.208845208845209,
+      "grad_norm": 0.8040947914123535,
+      "learning_rate": 0.0002,
+      "loss": 0.3369,
+      "step": 4240
+    },
+    {
+      "epoch": 5.221130221130221,
+      "grad_norm": 0.7827144265174866,
+      "learning_rate": 0.0002,
+      "loss": 0.3496,
+      "step": 4250
+    },
+    {
+      "epoch": 5.233415233415234,
+      "grad_norm": 0.7306333184242249,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4260
+    },
+    {
+      "epoch": 5.245700245700245,
+      "grad_norm": 1.0963380336761475,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4270
+    },
+    {
+      "epoch": 5.257985257985258,
+      "grad_norm": 0.8200454711914062,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4280
+    },
+    {
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.8666796684265137,
+      "learning_rate": 0.0002,
+      "loss": 0.3509,
+      "step": 4290
+    },
+    {
+      "epoch": 5.282555282555283,
+      "grad_norm": 0.7862894535064697,
+      "learning_rate": 0.0002,
+      "loss": 0.3423,
+      "step": 4300
+    },
+    {
+      "epoch": 5.294840294840295,
+      "grad_norm": 0.8163095712661743,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4310
+    },
+    {
+      "epoch": 5.3071253071253075,
+      "grad_norm": 0.8069050908088684,
+      "learning_rate": 0.0002,
+      "loss": 0.34,
+      "step": 4320
+    },
+    {
+      "epoch": 5.319410319410319,
+      "grad_norm": 0.7858486175537109,
+      "learning_rate": 0.0002,
+      "loss": 0.3532,
+      "step": 4330
+    },
+    {
+      "epoch": 5.3316953316953315,
+      "grad_norm": 0.950339674949646,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4340
+    },
+    {
+      "epoch": 5.343980343980344,
+      "grad_norm": 0.9056477546691895,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4350
+    },
+    {
+      "epoch": 5.356265356265356,
+      "grad_norm": 0.9619399905204773,
+      "learning_rate": 0.0002,
+      "loss": 0.3538,
+      "step": 4360
+    },
+    {
+      "epoch": 5.368550368550369,
+      "grad_norm": 0.9778652191162109,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4370
+    },
+    {
+      "epoch": 5.38083538083538,
+      "grad_norm": 0.6919555068016052,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4380
+    },
+    {
+      "epoch": 5.393120393120393,
+      "grad_norm": 0.8121668696403503,
+      "learning_rate": 0.0002,
+      "loss": 0.3426,
+      "step": 4390
+    },
+    {
+      "epoch": 5.405405405405405,
+      "grad_norm": 0.8481289148330688,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4400
+    },
+    {
+      "epoch": 5.417690417690418,
+      "grad_norm": 0.8727408647537231,
+      "learning_rate": 0.0002,
+      "loss": 0.345,
+      "step": 4410
+    },
+    {
+      "epoch": 5.42997542997543,
+      "grad_norm": 0.8920271396636963,
+      "learning_rate": 0.0002,
+      "loss": 0.3554,
+      "step": 4420
+    },
+    {
+      "epoch": 5.442260442260443,
+      "grad_norm": 0.7758749723434448,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4430
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.8847506642341614,
+      "learning_rate": 0.0002,
+      "loss": 0.3483,
+      "step": 4440
+    },
+    {
+      "epoch": 5.466830466830467,
+      "grad_norm": 0.9760470390319824,
+      "learning_rate": 0.0002,
+      "loss": 0.3557,
+      "step": 4450
+    },
+    {
+      "epoch": 5.479115479115479,
+      "grad_norm": 0.8940271139144897,
+      "learning_rate": 0.0002,
+      "loss": 0.3536,
+      "step": 4460
+    },
+    {
+      "epoch": 5.4914004914004915,
+      "grad_norm": 0.8668502569198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 4470
+    },
+    {
+      "epoch": 5.503685503685504,
+      "grad_norm": 0.9097439050674438,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4480
+    },
+    {
+      "epoch": 5.515970515970516,
+      "grad_norm": 0.8217208981513977,
+      "learning_rate": 0.0002,
+      "loss": 0.3417,
+      "step": 4490
+    },
+    {
+      "epoch": 5.528255528255528,
+      "grad_norm": 0.7853189706802368,
+      "learning_rate": 0.0002,
+      "loss": 0.3482,
+      "step": 4500
+    },
+    {
+      "epoch": 5.54054054054054,
+      "grad_norm": 1.1113477945327759,
+      "learning_rate": 0.0002,
+      "loss": 0.3479,
+      "step": 4510
+    },
+    {
+      "epoch": 5.552825552825553,
+      "grad_norm": 0.8637538552284241,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4520
+    },
+    {
+      "epoch": 5.565110565110565,
+      "grad_norm": 1.0230066776275635,
+      "learning_rate": 0.0002,
+      "loss": 0.3403,
+      "step": 4530
+    },
+    {
+      "epoch": 5.577395577395578,
+      "grad_norm": 0.8972793817520142,
+      "learning_rate": 0.0002,
+      "loss": 0.3588,
+      "step": 4540
+    },
+    {
+      "epoch": 5.58968058968059,
+      "grad_norm": 0.7950642704963684,
+      "learning_rate": 0.0002,
+      "loss": 0.3428,
+      "step": 4550
+    },
+    {
+      "epoch": 5.601965601965602,
+      "grad_norm": 1.113753318786621,
+      "learning_rate": 0.0002,
+      "loss": 0.3468,
+      "step": 4560
+    },
+    {
+      "epoch": 5.614250614250614,
+      "grad_norm": 0.7842669486999512,
+      "learning_rate": 0.0002,
+      "loss": 0.3354,
+      "step": 4570
+    },
+    {
+      "epoch": 5.6265356265356266,
+      "grad_norm": 0.9713512063026428,
+      "learning_rate": 0.0002,
+      "loss": 0.3419,
+      "step": 4580
+    },
+    {
+      "epoch": 5.638820638820639,
+      "grad_norm": 0.9451650977134705,
+      "learning_rate": 0.0002,
+      "loss": 0.3502,
+      "step": 4590
+    },
+    {
+      "epoch": 5.651105651105651,
+      "grad_norm": 1.055484414100647,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4600
+    },
+    {
+      "epoch": 5.663390663390663,
+      "grad_norm": 0.8408507704734802,
+      "learning_rate": 0.0002,
+      "loss": 0.3436,
+      "step": 4610
+    },
+    {
+      "epoch": 5.675675675675675,
+      "grad_norm": 1.0293926000595093,
+      "learning_rate": 0.0002,
+      "loss": 0.3619,
+      "step": 4620
+    },
+    {
+      "epoch": 5.687960687960688,
+      "grad_norm": 0.7198245525360107,
+      "learning_rate": 0.0002,
+      "loss": 0.3484,
+      "step": 4630
+    },
+    {
+      "epoch": 5.7002457002457,
+      "grad_norm": 0.7564466595649719,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 4640
+    },
+    {
+      "epoch": 5.712530712530713,
+      "grad_norm": 0.7980002760887146,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4650
+    },
+    {
+      "epoch": 5.724815724815725,
+      "grad_norm": 0.8685088753700256,
+      "learning_rate": 0.0002,
+      "loss": 0.3478,
+      "step": 4660
+    },
+    {
+      "epoch": 5.737100737100737,
+      "grad_norm": 0.8816949129104614,
+      "learning_rate": 0.0002,
+      "loss": 0.3692,
+      "step": 4670
+    },
+    {
+      "epoch": 5.749385749385749,
+      "grad_norm": 0.7154731750488281,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4680
+    },
+    {
+      "epoch": 5.761670761670762,
+      "grad_norm": 0.9430679678916931,
+      "learning_rate": 0.0002,
+      "loss": 0.3503,
+      "step": 4690
+    },
+    {
+      "epoch": 5.773955773955774,
+      "grad_norm": 0.7640151381492615,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4700
+    },
+    {
+      "epoch": 5.7862407862407865,
+      "grad_norm": 1.0920690298080444,
+      "learning_rate": 0.0002,
+      "loss": 0.3444,
+      "step": 4710
+    },
+    {
+      "epoch": 5.798525798525798,
+      "grad_norm": 0.9362104535102844,
+      "learning_rate": 0.0002,
+      "loss": 0.3356,
+      "step": 4720
+    },
+    {
+      "epoch": 5.8108108108108105,
+      "grad_norm": 0.8392294645309448,
+      "learning_rate": 0.0002,
+      "loss": 0.339,
+      "step": 4730
+    },
+    {
+      "epoch": 5.823095823095823,
+      "grad_norm": 0.9893582463264465,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 4740
+    },
+    {
+      "epoch": 5.835380835380835,
+      "grad_norm": 0.6985510587692261,
+      "learning_rate": 0.0002,
+      "loss": 0.3446,
+      "step": 4750
+    },
+    {
+      "epoch": 5.847665847665848,
+      "grad_norm": 0.8906862735748291,
+      "learning_rate": 0.0002,
+      "loss": 0.3534,
+      "step": 4760
+    },
+    {
+      "epoch": 5.85995085995086,
+      "grad_norm": 0.8036413192749023,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 4770
+    },
+    {
+      "epoch": 5.872235872235873,
+      "grad_norm": 0.9948155283927917,
+      "learning_rate": 0.0002,
+      "loss": 0.3326,
+      "step": 4780
+    },
+    {
+      "epoch": 5.884520884520884,
+      "grad_norm": 0.8618432283401489,
+      "learning_rate": 0.0002,
+      "loss": 0.3385,
+      "step": 4790
+    },
+    {
+      "epoch": 5.896805896805897,
+      "grad_norm": 1.0422909259796143,
+      "learning_rate": 0.0002,
+      "loss": 0.3302,
+      "step": 4800
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 1.1892569065093994,
+      "learning_rate": 0.0002,
+      "loss": 0.3448,
+      "step": 4810
+    },
+    {
+      "epoch": 5.921375921375922,
+      "grad_norm": 1.1459916830062866,
+      "learning_rate": 0.0002,
+      "loss": 0.3506,
+      "step": 4820
+    },
+    {
+      "epoch": 5.933660933660933,
+      "grad_norm": 1.056235909461975,
+      "learning_rate": 0.0002,
+      "loss": 0.3387,
+      "step": 4830
+    },
+    {
+      "epoch": 5.945945945945946,
+      "grad_norm": 0.8517277240753174,
+      "learning_rate": 0.0002,
+      "loss": 0.344,
+      "step": 4840
+    },
+    {
+      "epoch": 5.958230958230958,
+      "grad_norm": 0.8153380751609802,
+      "learning_rate": 0.0002,
+      "loss": 0.3421,
+      "step": 4850
+    },
+    {
+      "epoch": 5.9705159705159705,
+      "grad_norm": 0.7907533049583435,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4860
+    },
+    {
+      "epoch": 5.982800982800983,
+      "grad_norm": 0.8443069458007812,
+      "learning_rate": 0.0002,
+      "loss": 0.3337,
+      "step": 4870
+    },
+    {
+      "epoch": 5.995085995085995,
+      "grad_norm": 0.8711344003677368,
+      "learning_rate": 0.0002,
+      "loss": 0.3351,
+      "step": 4880
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.3778059184551239,
+      "eval_runtime": 20.6858,
+      "eval_samples_per_second": 16.001,
+      "eval_steps_per_second": 2.03,
+      "step": 4884
+    },
+    {
+      "epoch": 6.007371007371007,
+      "grad_norm": 0.7697948813438416,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 4890
+    },
+    {
+      "epoch": 6.019656019656019,
+      "grad_norm": 0.7734108567237854,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 4900
+    },
+    {
+      "epoch": 6.031941031941032,
+      "grad_norm": 0.7173922657966614,
+      "learning_rate": 0.0002,
+      "loss": 0.3242,
+      "step": 4910
+    },
+    {
+      "epoch": 6.044226044226044,
+      "grad_norm": 1.062118649482727,
+      "learning_rate": 0.0002,
+      "loss": 0.3159,
+      "step": 4920
+    },
+    {
+      "epoch": 6.056511056511057,
+      "grad_norm": 0.746422529220581,
+      "learning_rate": 0.0002,
+      "loss": 0.3361,
+      "step": 4930
+    },
+    {
+      "epoch": 6.068796068796069,
+      "grad_norm": 0.8549448251724243,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 4940
+    },
+    {
+      "epoch": 6.081081081081081,
+      "grad_norm": 0.9405432939529419,
+      "learning_rate": 0.0002,
+      "loss": 0.3236,
+      "step": 4950
+    },
+    {
+      "epoch": 6.093366093366093,
+      "grad_norm": 0.752382755279541,
+      "learning_rate": 0.0002,
+      "loss": 0.3278,
+      "step": 4960
+    },
+    {
+      "epoch": 6.105651105651106,
+      "grad_norm": 0.820332407951355,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 4970
+    },
+    {
+      "epoch": 6.117936117936118,
+      "grad_norm": 0.8701449036598206,
+      "learning_rate": 0.0002,
+      "loss": 0.3192,
+      "step": 4980
+    },
+    {
+      "epoch": 6.1302211302211305,
+      "grad_norm": 0.8192865252494812,
+      "learning_rate": 0.0002,
+      "loss": 0.321,
+      "step": 4990
+    },
+    {
+      "epoch": 6.142506142506143,
+      "grad_norm": 1.0016303062438965,
+      "learning_rate": 0.0002,
+      "loss": 0.3295,
+      "step": 5000
+    },
+    {
+      "epoch": 6.1547911547911545,
+      "grad_norm": 0.9194409251213074,
+      "learning_rate": 0.0002,
+      "loss": 0.3352,
+      "step": 5010
+    },
+    {
+      "epoch": 6.167076167076167,
+      "grad_norm": 0.9319757223129272,
+      "learning_rate": 0.0002,
+      "loss": 0.3205,
+      "step": 5020
+    },
+    {
+      "epoch": 6.179361179361179,
+      "grad_norm": 0.8737656474113464,
+      "learning_rate": 0.0002,
+      "loss": 0.3256,
+      "step": 5030
+    },
+    {
+      "epoch": 6.191646191646192,
+      "grad_norm": 0.8736537098884583,
+      "learning_rate": 0.0002,
+      "loss": 0.3221,
+      "step": 5040
+    },
+    {
+      "epoch": 6.203931203931204,
+      "grad_norm": 0.9301430583000183,
+      "learning_rate": 0.0002,
+      "loss": 0.3265,
+      "step": 5050
+    },
+    {
+      "epoch": 6.216216216216216,
+      "grad_norm": 0.7717130780220032,
+      "learning_rate": 0.0002,
+      "loss": 0.3285,
+      "step": 5060
+    },
+    {
+      "epoch": 6.228501228501228,
+      "grad_norm": 0.6709604859352112,
+      "learning_rate": 0.0002,
+      "loss": 0.3192,
+      "step": 5070
+    },
+    {
+      "epoch": 6.240786240786241,
+      "grad_norm": 0.879374086856842,
+      "learning_rate": 0.0002,
+      "loss": 0.3352,
+      "step": 5080
+    },
+    {
+      "epoch": 6.253071253071253,
+      "grad_norm": 0.9136955738067627,
+      "learning_rate": 0.0002,
+      "loss": 0.329,
+      "step": 5090
+    },
+    {
+      "epoch": 6.2653562653562656,
+      "grad_norm": 0.795177161693573,
+      "learning_rate": 0.0002,
+      "loss": 0.3228,
+      "step": 5100
+    },
+    {
+      "epoch": 6.277641277641278,
+      "grad_norm": 1.0412259101867676,
+      "learning_rate": 0.0002,
+      "loss": 0.3273,
+      "step": 5110
+    },
+    {
+      "epoch": 6.2899262899262895,
+      "grad_norm": 0.7382524013519287,
+      "learning_rate": 0.0002,
+      "loss": 0.3221,
+      "step": 5120
+    },
+    {
+      "epoch": 6.302211302211302,
+      "grad_norm": 0.8818480968475342,
+      "learning_rate": 0.0002,
+      "loss": 0.3102,
+      "step": 5130
+    },
+    {
+      "epoch": 6.314496314496314,
+      "grad_norm": 0.7865153551101685,
+      "learning_rate": 0.0002,
+      "loss": 0.3316,
+      "step": 5140
+    },
+    {
+      "epoch": 6.326781326781327,
+      "grad_norm": 0.9166486859321594,
+      "learning_rate": 0.0002,
+      "loss": 0.3264,
+      "step": 5150
+    },
+    {
+      "epoch": 6.339066339066339,
+      "grad_norm": 0.6655149459838867,
+      "learning_rate": 0.0002,
+      "loss": 0.33,
+      "step": 5160
+    },
+    {
+      "epoch": 6.351351351351352,
+      "grad_norm": 0.7762818336486816,
+      "learning_rate": 0.0002,
+      "loss": 0.3359,
+      "step": 5170
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.8057235479354858,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 5180
+    },
+    {
+      "epoch": 6.375921375921376,
+      "grad_norm": 0.8186984062194824,
+      "learning_rate": 0.0002,
+      "loss": 0.3167,
+      "step": 5190
+    },
+    {
+      "epoch": 6.388206388206388,
+      "grad_norm": 0.8669573068618774,
+      "learning_rate": 0.0002,
+      "loss": 0.3289,
+      "step": 5200
+    },
+    {
+      "epoch": 6.400491400491401,
+      "grad_norm": 0.8904402852058411,
+      "learning_rate": 0.0002,
+      "loss": 0.3313,
+      "step": 5210
+    },
+    {
+      "epoch": 6.412776412776413,
+      "grad_norm": 0.9250359535217285,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 5220
+    },
+    {
+      "epoch": 6.4250614250614255,
+      "grad_norm": 0.8718299269676208,
+      "learning_rate": 0.0002,
+      "loss": 0.3229,
+      "step": 5230
+    },
+    {
+      "epoch": 6.437346437346437,
+      "grad_norm": 0.8156430125236511,
+      "learning_rate": 0.0002,
+      "loss": 0.3214,
+      "step": 5240
+    },
+    {
+      "epoch": 6.4496314496314495,
+      "grad_norm": 0.7759218215942383,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 5250
+    },
+    {
+      "epoch": 6.461916461916462,
+      "grad_norm": 0.8137310743331909,
+      "learning_rate": 0.0002,
+      "loss": 0.3298,
+      "step": 5260
+    },
+    {
+      "epoch": 6.474201474201474,
+      "grad_norm": 0.8121917843818665,
+      "learning_rate": 0.0002,
+      "loss": 0.3275,
+      "step": 5270
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 0.8178010582923889,
+      "learning_rate": 0.0002,
+      "loss": 0.3201,
+      "step": 5280
+    },
+    {
+      "epoch": 6.498771498771498,
+      "grad_norm": 1.1806302070617676,
+      "learning_rate": 0.0002,
+      "loss": 0.3271,
+      "step": 5290
+    },
+    {
+      "epoch": 6.511056511056511,
+      "grad_norm": 0.8255127668380737,
+      "learning_rate": 0.0002,
+      "loss": 0.3231,
+      "step": 5300
+    },
+    {
+      "epoch": 6.523341523341523,
+      "grad_norm": 0.8006690740585327,
+      "learning_rate": 0.0002,
+      "loss": 0.3227,
+      "step": 5310
+    },
+    {
+      "epoch": 6.535626535626536,
+      "grad_norm": 0.9932374358177185,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 5320
+    },
+    {
+      "epoch": 6.547911547911548,
+      "grad_norm": 0.8973969221115112,
+      "learning_rate": 0.0002,
+      "loss": 0.3291,
+      "step": 5330
+    },
+    {
+      "epoch": 6.560196560196561,
+      "grad_norm": 0.7359915971755981,
+      "learning_rate": 0.0002,
+      "loss": 0.3146,
+      "step": 5340
+    },
+    {
+      "epoch": 6.572481572481572,
+      "grad_norm": 0.9941133856773376,
+      "learning_rate": 0.0002,
+      "loss": 0.3308,
+      "step": 5350
+    },
+    {
+      "epoch": 6.584766584766585,
+      "grad_norm": 0.9008874893188477,
+      "learning_rate": 0.0002,
+      "loss": 0.3202,
+      "step": 5360
+    },
+    {
+      "epoch": 6.597051597051597,
+      "grad_norm": 1.309710144996643,
+      "learning_rate": 0.0002,
+      "loss": 0.3271,
+      "step": 5370
+    },
+    {
+      "epoch": 6.6093366093366095,
+      "grad_norm": 0.797768235206604,
+      "learning_rate": 0.0002,
+      "loss": 0.3177,
+      "step": 5380
+    },
+    {
+      "epoch": 6.621621621621622,
+      "grad_norm": 0.8507353663444519,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5390
+    },
+    {
+      "epoch": 6.6339066339066335,
+      "grad_norm": 0.9628674983978271,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 5400
+    },
+    {
+      "epoch": 6.646191646191646,
+      "grad_norm": 0.6989983320236206,
+      "learning_rate": 0.0002,
+      "loss": 0.3155,
+      "step": 5410
+    },
+    {
+      "epoch": 6.658476658476658,
+      "grad_norm": 0.9505863189697266,
+      "learning_rate": 0.0002,
+      "loss": 0.3197,
+      "step": 5420
+    },
+    {
+      "epoch": 6.670761670761671,
+      "grad_norm": 0.8058171272277832,
+      "learning_rate": 0.0002,
+      "loss": 0.3259,
+      "step": 5430
+    },
+    {
+      "epoch": 6.683046683046683,
+      "grad_norm": 0.8476499915122986,
+      "learning_rate": 0.0002,
+      "loss": 0.3248,
+      "step": 5440
+    },
+    {
+      "epoch": 6.695331695331696,
+      "grad_norm": 0.8503309488296509,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 5450
+    },
+    {
+      "epoch": 6.707616707616707,
+      "grad_norm": 0.919566810131073,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5460
+    },
+    {
+      "epoch": 6.71990171990172,
+      "grad_norm": 0.7741201519966125,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5470
+    },
+    {
+      "epoch": 6.732186732186732,
+      "grad_norm": 0.8432701826095581,
+      "learning_rate": 0.0002,
+      "loss": 0.329,
+      "step": 5480
+    },
+    {
+      "epoch": 6.744471744471745,
+      "grad_norm": 1.0183148384094238,
+      "learning_rate": 0.0002,
+      "loss": 0.3284,
+      "step": 5490
+    },
+    {
+      "epoch": 6.756756756756757,
+      "grad_norm": 0.8491143584251404,
+      "learning_rate": 0.0002,
+      "loss": 0.3312,
+      "step": 5500
+    },
+    {
+      "epoch": 6.769041769041769,
+      "grad_norm": 0.9586310386657715,
+      "learning_rate": 0.0002,
+      "loss": 0.3208,
+      "step": 5510
+    },
+    {
+      "epoch": 6.781326781326781,
+      "grad_norm": 0.7936097383499146,
+      "learning_rate": 0.0002,
+      "loss": 0.3305,
+      "step": 5520
+    },
+    {
+      "epoch": 6.7936117936117935,
+      "grad_norm": 0.7875059247016907,
+      "learning_rate": 0.0002,
+      "loss": 0.318,
+      "step": 5530
+    },
+    {
+      "epoch": 6.805896805896806,
+      "grad_norm": 0.8136157393455505,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 5540
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.837213933467865,
+      "learning_rate": 0.0002,
+      "loss": 0.3161,
+      "step": 5550
+    },
+    {
+      "epoch": 6.830466830466831,
+      "grad_norm": 0.6812925338745117,
+      "learning_rate": 0.0002,
+      "loss": 0.3153,
+      "step": 5560
+    },
+    {
+      "epoch": 6.842751842751843,
+      "grad_norm": 0.7309592962265015,
+      "learning_rate": 0.0002,
+      "loss": 0.3139,
+      "step": 5570
+    },
+    {
+      "epoch": 6.855036855036855,
+      "grad_norm": 0.6905979514122009,
+      "learning_rate": 0.0002,
+      "loss": 0.3126,
+      "step": 5580
+    },
+    {
+      "epoch": 6.867321867321867,
+      "grad_norm": 1.1768406629562378,
+      "learning_rate": 0.0002,
+      "loss": 0.3291,
+      "step": 5590
+    },
+    {
+      "epoch": 6.87960687960688,
+      "grad_norm": 0.7618567943572998,
+      "learning_rate": 0.0002,
+      "loss": 0.3193,
+      "step": 5600
+    },
+    {
+      "epoch": 6.891891891891892,
+      "grad_norm": 0.7930929660797119,
+      "learning_rate": 0.0002,
+      "loss": 0.3296,
+      "step": 5610
+    },
+    {
+      "epoch": 6.9041769041769046,
+      "grad_norm": 0.7931787371635437,
+      "learning_rate": 0.0002,
+      "loss": 0.3241,
+      "step": 5620
+    },
+    {
+      "epoch": 6.916461916461916,
+      "grad_norm": 0.6366972923278809,
+      "learning_rate": 0.0002,
+      "loss": 0.3215,
+      "step": 5630
+    },
+    {
+      "epoch": 6.9287469287469285,
+      "grad_norm": 0.7782737612724304,
+      "learning_rate": 0.0002,
+      "loss": 0.3264,
+      "step": 5640
+    },
+    {
+      "epoch": 6.941031941031941,
+      "grad_norm": 0.8643787503242493,
+      "learning_rate": 0.0002,
+      "loss": 0.3186,
+      "step": 5650
+    },
+    {
+      "epoch": 6.953316953316953,
+      "grad_norm": 1.0843733549118042,
+      "learning_rate": 0.0002,
+      "loss": 0.3285,
+      "step": 5660
+    },
+    {
+      "epoch": 6.965601965601966,
+      "grad_norm": 0.71319180727005,
+      "learning_rate": 0.0002,
+      "loss": 0.3163,
+      "step": 5670
+    },
+    {
+      "epoch": 6.977886977886978,
+      "grad_norm": 0.976536750793457,
+      "learning_rate": 0.0002,
+      "loss": 0.3196,
+      "step": 5680
+    },
+    {
+      "epoch": 6.99017199017199,
+      "grad_norm": 0.9221968054771423,
+      "learning_rate": 0.0002,
+      "loss": 0.3255,
+      "step": 5690
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.3616626560688019,
+      "eval_runtime": 20.8747,
+      "eval_samples_per_second": 15.857,
+      "eval_steps_per_second": 2.012,
+      "step": 5698
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 6.964093511742259e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..952cf5145a9d7e80dc7491c40196d56467129957
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34589486cf3edd2be3ba9bcb7e87563196b7a9856dd90683bdf986b557d160d3
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f1bf087da1004aab0e3f30c9e9fef9b06a5a3f8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ba0cfae53e85afd2511561a38a6f578a5bc0a036eecc8e2bd842ec8dbb8679
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..459298bb39602affb600d0808d13fa7d1ce72240
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430471ab88b23b53bb64769e9f9baf75a650e45afe6ed9ee8dbf521fa822e78e
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ebe13cf064eed1a29ad4b1fc8ba5b1a8bce7e6cf
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85386f3e84bf3fcbddc99632d468aef6e17dd9860afd628d6b9c360a7a9b8cfe
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..af95cf5b26586ddc33c849b4bbaba306e5398ca9
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/trainer_state.json
@@ -0,0 +1,4654 @@
+{
+  "best_metric": 0.3476468026638031,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512",
+  "epoch": 8.0,
+  "eval_steps": 10,
+  "global_step": 6512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    },
+    {
+      "epoch": 1.0073710073710074,
+      "grad_norm": 0.7405961751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.6959,
+      "step": 820
+    },
+    {
+      "epoch": 1.0196560196560196,
+      "grad_norm": 0.8534344434738159,
+      "learning_rate": 0.0002,
+      "loss": 0.6706,
+      "step": 830
+    },
+    {
+      "epoch": 1.031941031941032,
+      "grad_norm": 0.7415764331817627,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 840
+    },
+    {
+      "epoch": 1.0442260442260443,
+      "grad_norm": 0.74293053150177,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 850
+    },
+    {
+      "epoch": 1.0565110565110565,
+      "grad_norm": 0.697727382183075,
+      "learning_rate": 0.0002,
+      "loss": 0.6897,
+      "step": 860
+    },
+    {
+      "epoch": 1.0687960687960687,
+      "grad_norm": 0.8022570013999939,
+      "learning_rate": 0.0002,
+      "loss": 0.6566,
+      "step": 870
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.7545800805091858,
+      "learning_rate": 0.0002,
+      "loss": 0.6759,
+      "step": 880
+    },
+    {
+      "epoch": 1.0933660933660934,
+      "grad_norm": 0.8005648255348206,
+      "learning_rate": 0.0002,
+      "loss": 0.6397,
+      "step": 890
+    },
+    {
+      "epoch": 1.1056511056511056,
+      "grad_norm": 0.7681778073310852,
+      "learning_rate": 0.0002,
+      "loss": 0.6499,
+      "step": 900
+    },
+    {
+      "epoch": 1.117936117936118,
+      "grad_norm": 0.7822468876838684,
+      "learning_rate": 0.0002,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.1302211302211302,
+      "grad_norm": 0.8324839472770691,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 920
+    },
+    {
+      "epoch": 1.1425061425061425,
+      "grad_norm": 0.8206289410591125,
+      "learning_rate": 0.0002,
+      "loss": 0.6659,
+      "step": 930
+    },
+    {
+      "epoch": 1.154791154791155,
+      "grad_norm": 0.786461591720581,
+      "learning_rate": 0.0002,
+      "loss": 0.6385,
+      "step": 940
+    },
+    {
+      "epoch": 1.1670761670761671,
+      "grad_norm": 0.8288539052009583,
+      "learning_rate": 0.0002,
+      "loss": 0.6493,
+      "step": 950
+    },
+    {
+      "epoch": 1.1793611793611793,
+      "grad_norm": 0.7566865682601929,
+      "learning_rate": 0.0002,
+      "loss": 0.6818,
+      "step": 960
+    },
+    {
+      "epoch": 1.1916461916461916,
+      "grad_norm": 0.7761894464492798,
+      "learning_rate": 0.0002,
+      "loss": 0.6597,
+      "step": 970
+    },
+    {
+      "epoch": 1.203931203931204,
+      "grad_norm": 0.7608440518379211,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 980
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.799745500087738,
+      "learning_rate": 0.0002,
+      "loss": 0.7041,
+      "step": 990
+    },
+    {
+      "epoch": 1.2285012285012284,
+      "grad_norm": 0.8135330677032471,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2407862407862407,
+      "grad_norm": 0.7410391569137573,
+      "learning_rate": 0.0002,
+      "loss": 0.6496,
+      "step": 1010
+    },
+    {
+      "epoch": 1.253071253071253,
+      "grad_norm": 0.7826172709465027,
+      "learning_rate": 0.0002,
+      "loss": 0.63,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2653562653562653,
+      "grad_norm": 0.7210677862167358,
+      "learning_rate": 0.0002,
+      "loss": 0.6582,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2776412776412776,
+      "grad_norm": 0.7571766972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.6609,
+      "step": 1040
+    },
+    {
+      "epoch": 1.28992628992629,
+      "grad_norm": 0.8602666258811951,
+      "learning_rate": 0.0002,
+      "loss": 0.6315,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3022113022113022,
+      "grad_norm": 0.8640648722648621,
+      "learning_rate": 0.0002,
+      "loss": 0.6825,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3144963144963144,
+      "grad_norm": 0.7289374470710754,
+      "learning_rate": 0.0002,
+      "loss": 0.6563,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3267813267813269,
+      "grad_norm": 0.8099908828735352,
+      "learning_rate": 0.0002,
+      "loss": 0.629,
+      "step": 1080
+    },
+    {
+      "epoch": 1.339066339066339,
+      "grad_norm": 0.8623505234718323,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.900576114654541,
+      "learning_rate": 0.0002,
+      "loss": 0.6368,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.729603111743927,
+      "learning_rate": 0.0002,
+      "loss": 0.6398,
+      "step": 1110
+    },
+    {
+      "epoch": 1.375921375921376,
+      "grad_norm": 0.8350434303283691,
+      "learning_rate": 0.0002,
+      "loss": 0.6619,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3882063882063882,
+      "grad_norm": 0.8049437999725342,
+      "learning_rate": 0.0002,
+      "loss": 0.6447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.4004914004914004,
+      "grad_norm": 0.8222764134407043,
+      "learning_rate": 0.0002,
+      "loss": 0.6336,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4127764127764126,
+      "grad_norm": 0.7949751019477844,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 1150
+    },
+    {
+      "epoch": 1.425061425061425,
+      "grad_norm": 0.8375639915466309,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4373464373464373,
+      "grad_norm": 0.7261053919792175,
+      "learning_rate": 0.0002,
+      "loss": 0.6358,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4496314496314495,
+      "grad_norm": 0.6918320655822754,
+      "learning_rate": 0.0002,
+      "loss": 0.6709,
+      "step": 1180
+    },
+    {
+      "epoch": 1.461916461916462,
+      "grad_norm": 0.8148727416992188,
+      "learning_rate": 0.0002,
+      "loss": 0.598,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4742014742014742,
+      "grad_norm": 0.7014724612236023,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.8110846281051636,
+      "learning_rate": 0.0002,
+      "loss": 0.617,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4987714987714988,
+      "grad_norm": 0.8336407542228699,
+      "learning_rate": 0.0002,
+      "loss": 0.6633,
+      "step": 1220
+    },
+    {
+      "epoch": 1.511056511056511,
+      "grad_norm": 0.826996386051178,
+      "learning_rate": 0.0002,
+      "loss": 0.6028,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5233415233415233,
+      "grad_norm": 0.7503120303153992,
+      "learning_rate": 0.0002,
+      "loss": 0.6464,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5356265356265357,
+      "grad_norm": 0.8297192454338074,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.547911547911548,
+      "grad_norm": 0.7585996985435486,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5601965601965602,
+      "grad_norm": 0.7530493140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.6196,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5724815724815726,
+      "grad_norm": 0.8141939640045166,
+      "learning_rate": 0.0002,
+      "loss": 0.6252,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5847665847665846,
+      "grad_norm": 0.6959931254386902,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 1290
+    },
+    {
+      "epoch": 1.597051597051597,
+      "grad_norm": 0.8677428364753723,
+      "learning_rate": 0.0002,
+      "loss": 0.6542,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6093366093366095,
+      "grad_norm": 0.8527476787567139,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8462157845497131,
+      "learning_rate": 0.0002,
+      "loss": 0.6393,
+      "step": 1320
+    },
+    {
+      "epoch": 1.633906633906634,
+      "grad_norm": 0.9371153712272644,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6461916461916462,
+      "grad_norm": 0.8408344984054565,
+      "learning_rate": 0.0002,
+      "loss": 0.5952,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6584766584766584,
+      "grad_norm": 0.8391859531402588,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6707616707616708,
+      "grad_norm": 0.7630598545074463,
+      "learning_rate": 0.0002,
+      "loss": 0.6313,
+      "step": 1360
+    },
+    {
+      "epoch": 1.683046683046683,
+      "grad_norm": 0.8007895350456238,
+      "learning_rate": 0.0002,
+      "loss": 0.5989,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6953316953316953,
+      "grad_norm": 0.7547900080680847,
+      "learning_rate": 0.0002,
+      "loss": 0.6094,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7076167076167077,
+      "grad_norm": 0.7779742479324341,
+      "learning_rate": 0.0002,
+      "loss": 0.6335,
+      "step": 1390
+    },
+    {
+      "epoch": 1.71990171990172,
+      "grad_norm": 0.712293803691864,
+      "learning_rate": 0.0002,
+      "loss": 0.6078,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7321867321867321,
+      "grad_norm": 0.8503297567367554,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7444717444717446,
+      "grad_norm": 0.8312245607376099,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.7758049368858337,
+      "learning_rate": 0.0002,
+      "loss": 0.5978,
+      "step": 1430
+    },
+    {
+      "epoch": 1.769041769041769,
+      "grad_norm": 0.8695956468582153,
+      "learning_rate": 0.0002,
+      "loss": 0.5822,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7813267813267815,
+      "grad_norm": 0.7785261273384094,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7936117936117935,
+      "grad_norm": 0.7091802358627319,
+      "learning_rate": 0.0002,
+      "loss": 0.6177,
+      "step": 1460
+    },
+    {
+      "epoch": 1.805896805896806,
+      "grad_norm": 0.774146556854248,
+      "learning_rate": 0.0002,
+      "loss": 0.5811,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8342524170875549,
+      "learning_rate": 0.0002,
+      "loss": 0.5833,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8304668304668303,
+      "grad_norm": 0.8087738156318665,
+      "learning_rate": 0.0002,
+      "loss": 0.634,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8427518427518428,
+      "grad_norm": 0.9830479621887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5961,
+      "step": 1500
+    },
+    {
+      "epoch": 1.855036855036855,
+      "grad_norm": 0.8537567853927612,
+      "learning_rate": 0.0002,
+      "loss": 0.6211,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8673218673218672,
+      "grad_norm": 0.8004562854766846,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8796068796068797,
+      "grad_norm": 0.8161284327507019,
+      "learning_rate": 0.0002,
+      "loss": 0.604,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.8688093423843384,
+      "learning_rate": 0.0002,
+      "loss": 0.5808,
+      "step": 1540
+    },
+    {
+      "epoch": 1.904176904176904,
+      "grad_norm": 0.8287379741668701,
+      "learning_rate": 0.0002,
+      "loss": 0.5663,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9164619164619165,
+      "grad_norm": 0.8050342202186584,
+      "learning_rate": 0.0002,
+      "loss": 0.5963,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9287469287469288,
+      "grad_norm": 0.9273895621299744,
+      "learning_rate": 0.0002,
+      "loss": 0.5837,
+      "step": 1570
+    },
+    {
+      "epoch": 1.941031941031941,
+      "grad_norm": 0.8416891694068909,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9533169533169534,
+      "grad_norm": 0.7299820184707642,
+      "learning_rate": 0.0002,
+      "loss": 0.5838,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9656019656019657,
+      "grad_norm": 0.7262272834777832,
+      "learning_rate": 0.0002,
+      "loss": 0.6025,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9778869778869779,
+      "grad_norm": 0.8649004697799683,
+      "learning_rate": 0.0002,
+      "loss": 0.5873,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9901719901719903,
+      "grad_norm": 0.8165444731712341,
+      "learning_rate": 0.0002,
+      "loss": 0.5764,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5858802795410156,
+      "eval_runtime": 22.6585,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 1.854,
+      "step": 1628
+    },
+    {
+      "epoch": 2.0024570024570023,
+      "grad_norm": 0.8142582178115845,
+      "learning_rate": 0.0002,
+      "loss": 0.5803,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0147420147420148,
+      "grad_norm": 1.0637224912643433,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1640
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.8923280239105225,
+      "learning_rate": 0.0002,
+      "loss": 0.5556,
+      "step": 1650
+    },
+    {
+      "epoch": 2.039312039312039,
+      "grad_norm": 0.8169175386428833,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0515970515970516,
+      "grad_norm": 0.8124040365219116,
+      "learning_rate": 0.0002,
+      "loss": 0.552,
+      "step": 1670
+    },
+    {
+      "epoch": 2.063882063882064,
+      "grad_norm": 0.9228773713111877,
+      "learning_rate": 0.0002,
+      "loss": 0.5259,
+      "step": 1680
+    },
+    {
+      "epoch": 2.076167076167076,
+      "grad_norm": 0.7216871380805969,
+      "learning_rate": 0.0002,
+      "loss": 0.5571,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0884520884520885,
+      "grad_norm": 0.8679503202438354,
+      "learning_rate": 0.0002,
+      "loss": 0.523,
+      "step": 1700
+    },
+    {
+      "epoch": 2.100737100737101,
+      "grad_norm": 0.8627730011940002,
+      "learning_rate": 0.0002,
+      "loss": 0.5379,
+      "step": 1710
+    },
+    {
+      "epoch": 2.113022113022113,
+      "grad_norm": 0.9175152778625488,
+      "learning_rate": 0.0002,
+      "loss": 0.551,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1253071253071254,
+      "grad_norm": 0.7930372953414917,
+      "learning_rate": 0.0002,
+      "loss": 0.5378,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1375921375921374,
+      "grad_norm": 0.8370155692100525,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1740
+    },
+    {
+      "epoch": 2.14987714987715,
+      "grad_norm": 0.9121434688568115,
+      "learning_rate": 0.0002,
+      "loss": 0.5419,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.8703579306602478,
+      "learning_rate": 0.0002,
+      "loss": 0.5499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1744471744471743,
+      "grad_norm": 0.9270512461662292,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 1770
+    },
+    {
+      "epoch": 2.1867321867321867,
+      "grad_norm": 0.9372949600219727,
+      "learning_rate": 0.0002,
+      "loss": 0.5165,
+      "step": 1780
+    },
+    {
+      "epoch": 2.199017199017199,
+      "grad_norm": 0.8955178260803223,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1790
+    },
+    {
+      "epoch": 2.211302211302211,
+      "grad_norm": 0.846102237701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5356,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2235872235872236,
+      "grad_norm": 0.9186713099479675,
+      "learning_rate": 0.0002,
+      "loss": 0.5303,
+      "step": 1810
+    },
+    {
+      "epoch": 2.235872235872236,
+      "grad_norm": 0.7695123553276062,
+      "learning_rate": 0.0002,
+      "loss": 0.5223,
+      "step": 1820
+    },
+    {
+      "epoch": 2.248157248157248,
+      "grad_norm": 0.7340332865715027,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2604422604422605,
+      "grad_norm": 0.8933137655258179,
+      "learning_rate": 0.0002,
+      "loss": 0.5327,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.7705038189888,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 1850
+    },
+    {
+      "epoch": 2.285012285012285,
+      "grad_norm": 0.8396083116531372,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.7695736289024353,
+      "learning_rate": 0.0002,
+      "loss": 0.5335,
+      "step": 1870
+    },
+    {
+      "epoch": 2.30958230958231,
+      "grad_norm": 0.8535045385360718,
+      "learning_rate": 0.0002,
+      "loss": 0.5105,
+      "step": 1880
+    },
+    {
+      "epoch": 2.321867321867322,
+      "grad_norm": 0.8549142479896545,
+      "learning_rate": 0.0002,
+      "loss": 0.5202,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3341523341523343,
+      "grad_norm": 0.9124433994293213,
+      "learning_rate": 0.0002,
+      "loss": 0.5268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3464373464373462,
+      "grad_norm": 0.855523943901062,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3587223587223587,
+      "grad_norm": 0.810878336429596,
+      "learning_rate": 0.0002,
+      "loss": 0.5162,
+      "step": 1920
+    },
+    {
+      "epoch": 2.371007371007371,
+      "grad_norm": 0.7409024834632874,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 1930
+    },
+    {
+      "epoch": 2.383292383292383,
+      "grad_norm": 0.8080927729606628,
+      "learning_rate": 0.0002,
+      "loss": 0.5045,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3955773955773956,
+      "grad_norm": 0.9661469459533691,
+      "learning_rate": 0.0002,
+      "loss": 0.5032,
+      "step": 1950
+    },
+    {
+      "epoch": 2.407862407862408,
+      "grad_norm": 0.838766872882843,
+      "learning_rate": 0.0002,
+      "loss": 0.5019,
+      "step": 1960
+    },
+    {
+      "epoch": 2.42014742014742,
+      "grad_norm": 0.8737491965293884,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.8657792210578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5153,
+      "step": 1980
+    },
+    {
+      "epoch": 2.444717444717445,
+      "grad_norm": 0.8883858919143677,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 1990
+    },
+    {
+      "epoch": 2.457002457002457,
+      "grad_norm": 0.8647662997245789,
+      "learning_rate": 0.0002,
+      "loss": 0.5283,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4692874692874693,
+      "grad_norm": 0.896037757396698,
+      "learning_rate": 0.0002,
+      "loss": 0.518,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4815724815724813,
+      "grad_norm": 0.8079167008399963,
+      "learning_rate": 0.0002,
+      "loss": 0.5245,
+      "step": 2020
+    },
+    {
+      "epoch": 2.493857493857494,
+      "grad_norm": 1.0293292999267578,
+      "learning_rate": 0.0002,
+      "loss": 0.5311,
+      "step": 2030
+    },
+    {
+      "epoch": 2.506142506142506,
+      "grad_norm": 0.8459244966506958,
+      "learning_rate": 0.0002,
+      "loss": 0.5091,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5184275184275187,
+      "grad_norm": 0.9244982600212097,
+      "learning_rate": 0.0002,
+      "loss": 0.4922,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5307125307125307,
+      "grad_norm": 0.8245007991790771,
+      "learning_rate": 0.0002,
+      "loss": 0.5006,
+      "step": 2060
+    },
+    {
+      "epoch": 2.542997542997543,
+      "grad_norm": 0.8869297504425049,
+      "learning_rate": 0.0002,
+      "loss": 0.5229,
+      "step": 2070
+    },
+    {
+      "epoch": 2.555282555282555,
+      "grad_norm": 0.8620884418487549,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.8387904167175293,
+      "learning_rate": 0.0002,
+      "loss": 0.5239,
+      "step": 2090
+    },
+    {
+      "epoch": 2.57985257985258,
+      "grad_norm": 0.8353935480117798,
+      "learning_rate": 0.0002,
+      "loss": 0.4974,
+      "step": 2100
+    },
+    {
+      "epoch": 2.592137592137592,
+      "grad_norm": 1.0136934518814087,
+      "learning_rate": 0.0002,
+      "loss": 0.5038,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6044226044226044,
+      "grad_norm": 0.9387392997741699,
+      "learning_rate": 0.0002,
+      "loss": 0.513,
+      "step": 2120
+    },
+    {
+      "epoch": 2.616707616707617,
+      "grad_norm": 0.898697555065155,
+      "learning_rate": 0.0002,
+      "loss": 0.4971,
+      "step": 2130
+    },
+    {
+      "epoch": 2.628992628992629,
+      "grad_norm": 1.0145231485366821,
+      "learning_rate": 0.0002,
+      "loss": 0.4981,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6412776412776413,
+      "grad_norm": 0.8335273265838623,
+      "learning_rate": 0.0002,
+      "loss": 0.5151,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6535626535626538,
+      "grad_norm": 1.0198529958724976,
+      "learning_rate": 0.0002,
+      "loss": 0.5129,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6658476658476657,
+      "grad_norm": 0.8353323340415955,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 2170
+    },
+    {
+      "epoch": 2.678132678132678,
+      "grad_norm": 0.8831406831741333,
+      "learning_rate": 0.0002,
+      "loss": 0.4818,
+      "step": 2180
+    },
+    {
+      "epoch": 2.69041769041769,
+      "grad_norm": 0.7182748913764954,
+      "learning_rate": 0.0002,
+      "loss": 0.4858,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.7892552614212036,
+      "learning_rate": 0.0002,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 2.714987714987715,
+      "grad_norm": 1.0144033432006836,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.0913645029067993,
+      "learning_rate": 0.0002,
+      "loss": 0.4909,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7395577395577395,
+      "grad_norm": 1.014394998550415,
+      "learning_rate": 0.0002,
+      "loss": 0.5069,
+      "step": 2230
+    },
+    {
+      "epoch": 2.751842751842752,
+      "grad_norm": 0.8118020296096802,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2240
+    },
+    {
+      "epoch": 2.764127764127764,
+      "grad_norm": 0.9027737379074097,
+      "learning_rate": 0.0002,
+      "loss": 0.5088,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7764127764127764,
+      "grad_norm": 0.8017747402191162,
+      "learning_rate": 0.0002,
+      "loss": 0.5027,
+      "step": 2260
+    },
+    {
+      "epoch": 2.788697788697789,
+      "grad_norm": 0.788362979888916,
+      "learning_rate": 0.0002,
+      "loss": 0.4957,
+      "step": 2270
+    },
+    {
+      "epoch": 2.800982800982801,
+      "grad_norm": 0.8338918089866638,
+      "learning_rate": 0.0002,
+      "loss": 0.5047,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8132678132678133,
+      "grad_norm": 0.8773167729377747,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8255528255528253,
+      "grad_norm": 0.9319674372673035,
+      "learning_rate": 0.0002,
+      "loss": 0.4806,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.8632726073265076,
+      "learning_rate": 0.0002,
+      "loss": 0.4815,
+      "step": 2310
+    },
+    {
+      "epoch": 2.85012285012285,
+      "grad_norm": 0.785464882850647,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 2320
+    },
+    {
+      "epoch": 2.8624078624078626,
+      "grad_norm": 0.8159732818603516,
+      "learning_rate": 0.0002,
+      "loss": 0.4867,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8746928746928746,
+      "grad_norm": 0.8702368140220642,
+      "learning_rate": 0.0002,
+      "loss": 0.4796,
+      "step": 2340
+    },
+    {
+      "epoch": 2.886977886977887,
+      "grad_norm": 1.0456738471984863,
+      "learning_rate": 0.0002,
+      "loss": 0.474,
+      "step": 2350
+    },
+    {
+      "epoch": 2.899262899262899,
+      "grad_norm": 1.0855203866958618,
+      "learning_rate": 0.0002,
+      "loss": 0.4934,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9115479115479115,
+      "grad_norm": 0.9378156065940857,
+      "learning_rate": 0.0002,
+      "loss": 0.4758,
+      "step": 2370
+    },
+    {
+      "epoch": 2.923832923832924,
+      "grad_norm": 0.7390182018280029,
+      "learning_rate": 0.0002,
+      "loss": 0.4831,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9361179361179364,
+      "grad_norm": 0.7667133212089539,
+      "learning_rate": 0.0002,
+      "loss": 0.5066,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9484029484029484,
+      "grad_norm": 0.8633476495742798,
+      "learning_rate": 0.0002,
+      "loss": 0.4722,
+      "step": 2400
+    },
+    {
+      "epoch": 2.960687960687961,
+      "grad_norm": 1.0821104049682617,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 2410
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.8911418914794922,
+      "learning_rate": 0.0002,
+      "loss": 0.4882,
+      "step": 2420
+    },
+    {
+      "epoch": 2.9852579852579852,
+      "grad_norm": 0.8791135549545288,
+      "learning_rate": 0.0002,
+      "loss": 0.4819,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9975429975429977,
+      "grad_norm": 0.8066530823707581,
+      "learning_rate": 0.0002,
+      "loss": 0.4875,
+      "step": 2440
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49752503633499146,
+      "eval_runtime": 20.2911,
+      "eval_samples_per_second": 16.313,
+      "eval_steps_per_second": 2.07,
+      "step": 2442
+    },
+    {
+      "epoch": 3.0098280098280097,
+      "grad_norm": 0.7644656896591187,
+      "learning_rate": 0.0002,
+      "loss": 0.4362,
+      "step": 2450
+    },
+    {
+      "epoch": 3.022113022113022,
+      "grad_norm": 0.9077525734901428,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0343980343980346,
+      "grad_norm": 0.7859287261962891,
+      "learning_rate": 0.0002,
+      "loss": 0.422,
+      "step": 2470
+    },
+    {
+      "epoch": 3.0466830466830466,
+      "grad_norm": 1.1200323104858398,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 2480
+    },
+    {
+      "epoch": 3.058968058968059,
+      "grad_norm": 0.7570453882217407,
+      "learning_rate": 0.0002,
+      "loss": 0.4519,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0712530712530715,
+      "grad_norm": 0.9450915455818176,
+      "learning_rate": 0.0002,
+      "loss": 0.4351,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0835380835380835,
+      "grad_norm": 0.8303545117378235,
+      "learning_rate": 0.0002,
+      "loss": 0.4343,
+      "step": 2510
+    },
+    {
+      "epoch": 3.095823095823096,
+      "grad_norm": 0.8864443898200989,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2520
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.945324718952179,
+      "learning_rate": 0.0002,
+      "loss": 0.4601,
+      "step": 2530
+    },
+    {
+      "epoch": 3.1203931203931203,
+      "grad_norm": 1.0562494993209839,
+      "learning_rate": 0.0002,
+      "loss": 0.4345,
+      "step": 2540
+    },
+    {
+      "epoch": 3.1326781326781328,
+      "grad_norm": 0.8607500195503235,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2550
+    },
+    {
+      "epoch": 3.1449631449631448,
+      "grad_norm": 0.8719640374183655,
+      "learning_rate": 0.0002,
+      "loss": 0.456,
+      "step": 2560
+    },
+    {
+      "epoch": 3.157248157248157,
+      "grad_norm": 0.8647059202194214,
+      "learning_rate": 0.0002,
+      "loss": 0.4469,
+      "step": 2570
+    },
+    {
+      "epoch": 3.1695331695331697,
+      "grad_norm": 0.8346507549285889,
+      "learning_rate": 0.0002,
+      "loss": 0.4483,
+      "step": 2580
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 1.0208854675292969,
+      "learning_rate": 0.0002,
+      "loss": 0.4331,
+      "step": 2590
+    },
+    {
+      "epoch": 3.194103194103194,
+      "grad_norm": 0.7064385414123535,
+      "learning_rate": 0.0002,
+      "loss": 0.435,
+      "step": 2600
+    },
+    {
+      "epoch": 3.2063882063882065,
+      "grad_norm": 0.927347719669342,
+      "learning_rate": 0.0002,
+      "loss": 0.4541,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2186732186732185,
+      "grad_norm": 0.943517804145813,
+      "learning_rate": 0.0002,
+      "loss": 0.4561,
+      "step": 2620
+    },
+    {
+      "epoch": 3.230958230958231,
+      "grad_norm": 0.7837198376655579,
+      "learning_rate": 0.0002,
+      "loss": 0.4225,
+      "step": 2630
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.7752765417098999,
+      "learning_rate": 0.0002,
+      "loss": 0.4494,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2555282555282554,
+      "grad_norm": 0.8578953146934509,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2650
+    },
+    {
+      "epoch": 3.267813267813268,
+      "grad_norm": 1.0209529399871826,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2800982800982803,
+      "grad_norm": 0.9069030284881592,
+      "learning_rate": 0.0002,
+      "loss": 0.4517,
+      "step": 2670
+    },
+    {
+      "epoch": 3.2923832923832923,
+      "grad_norm": 0.8454729318618774,
+      "learning_rate": 0.0002,
+      "loss": 0.4262,
+      "step": 2680
+    },
+    {
+      "epoch": 3.3046683046683047,
+      "grad_norm": 0.8253099322319031,
+      "learning_rate": 0.0002,
+      "loss": 0.4349,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3169533169533167,
+      "grad_norm": 0.8765934109687805,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 2700
+    },
+    {
+      "epoch": 3.329238329238329,
+      "grad_norm": 0.8149126172065735,
+      "learning_rate": 0.0002,
+      "loss": 0.4518,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3415233415233416,
+      "grad_norm": 0.8820102214813232,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3538083538083536,
+      "grad_norm": 0.8813952803611755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 2730
+    },
+    {
+      "epoch": 3.366093366093366,
+      "grad_norm": 1.0338447093963623,
+      "learning_rate": 0.0002,
+      "loss": 0.4396,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8780209422111511,
+      "learning_rate": 0.0002,
+      "loss": 0.4468,
+      "step": 2750
+    },
+    {
+      "epoch": 3.3906633906633905,
+      "grad_norm": 0.9017151594161987,
+      "learning_rate": 0.0002,
+      "loss": 0.441,
+      "step": 2760
+    },
+    {
+      "epoch": 3.402948402948403,
+      "grad_norm": 0.8647638559341431,
+      "learning_rate": 0.0002,
+      "loss": 0.446,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4152334152334154,
+      "grad_norm": 0.8298183679580688,
+      "learning_rate": 0.0002,
+      "loss": 0.4131,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4275184275184274,
+      "grad_norm": 0.9298108816146851,
+      "learning_rate": 0.0002,
+      "loss": 0.4406,
+      "step": 2790
+    },
+    {
+      "epoch": 3.43980343980344,
+      "grad_norm": 0.8909980058670044,
+      "learning_rate": 0.0002,
+      "loss": 0.4145,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4520884520884523,
+      "grad_norm": 0.8027496933937073,
+      "learning_rate": 0.0002,
+      "loss": 0.4148,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4643734643734643,
+      "grad_norm": 0.8766195774078369,
+      "learning_rate": 0.0002,
+      "loss": 0.4244,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4766584766584767,
+      "grad_norm": 0.8194443583488464,
+      "learning_rate": 0.0002,
+      "loss": 0.4292,
+      "step": 2830
+    },
+    {
+      "epoch": 3.488943488943489,
+      "grad_norm": 0.9862873554229736,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 2840
+    },
+    {
+      "epoch": 3.501228501228501,
+      "grad_norm": 0.8755377531051636,
+      "learning_rate": 0.0002,
+      "loss": 0.4393,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.7300266027450562,
+      "learning_rate": 0.0002,
+      "loss": 0.4231,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5257985257985256,
+      "grad_norm": 0.8342461585998535,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 2870
+    },
+    {
+      "epoch": 3.538083538083538,
+      "grad_norm": 0.8624151349067688,
+      "learning_rate": 0.0002,
+      "loss": 0.4395,
+      "step": 2880
+    },
+    {
+      "epoch": 3.5503685503685505,
+      "grad_norm": 0.8931261301040649,
+      "learning_rate": 0.0002,
+      "loss": 0.4064,
+      "step": 2890
+    },
+    {
+      "epoch": 3.562653562653563,
+      "grad_norm": 0.8617086410522461,
+      "learning_rate": 0.0002,
+      "loss": 0.4358,
+      "step": 2900
+    },
+    {
+      "epoch": 3.574938574938575,
+      "grad_norm": 0.8754099607467651,
+      "learning_rate": 0.0002,
+      "loss": 0.419,
+      "step": 2910
+    },
+    {
+      "epoch": 3.5872235872235874,
+      "grad_norm": 0.8345834612846375,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2920
+    },
+    {
+      "epoch": 3.5995085995085994,
+      "grad_norm": 1.1414062976837158,
+      "learning_rate": 0.0002,
+      "loss": 0.4375,
+      "step": 2930
+    },
+    {
+      "epoch": 3.611793611793612,
+      "grad_norm": 0.994860053062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4297,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6240786240786242,
+      "grad_norm": 1.19268000125885,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.8399543762207031,
+      "learning_rate": 0.0002,
+      "loss": 0.4029,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.9873217940330505,
+      "learning_rate": 0.0002,
+      "loss": 0.4432,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6609336609336607,
+      "grad_norm": 0.9116013646125793,
+      "learning_rate": 0.0002,
+      "loss": 0.4308,
+      "step": 2980
+    },
+    {
+      "epoch": 3.673218673218673,
+      "grad_norm": 0.9503833651542664,
+      "learning_rate": 0.0002,
+      "loss": 0.4275,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6855036855036856,
+      "grad_norm": 0.9401112794876099,
+      "learning_rate": 0.0002,
+      "loss": 0.4306,
+      "step": 3000
+    },
+    {
+      "epoch": 3.697788697788698,
+      "grad_norm": 1.00745689868927,
+      "learning_rate": 0.0002,
+      "loss": 0.4333,
+      "step": 3010
+    },
+    {
+      "epoch": 3.71007371007371,
+      "grad_norm": 1.0553191900253296,
+      "learning_rate": 0.0002,
+      "loss": 0.432,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7223587223587224,
+      "grad_norm": 1.0226953029632568,
+      "learning_rate": 0.0002,
+      "loss": 0.4321,
+      "step": 3030
+    },
+    {
+      "epoch": 3.7346437346437344,
+      "grad_norm": 1.085554838180542,
+      "learning_rate": 0.0002,
+      "loss": 0.418,
+      "step": 3040
+    },
+    {
+      "epoch": 3.746928746928747,
+      "grad_norm": 0.9948731064796448,
+      "learning_rate": 0.0002,
+      "loss": 0.4196,
+      "step": 3050
+    },
+    {
+      "epoch": 3.7592137592137593,
+      "grad_norm": 0.9328727126121521,
+      "learning_rate": 0.0002,
+      "loss": 0.4281,
+      "step": 3060
+    },
+    {
+      "epoch": 3.7714987714987718,
+      "grad_norm": 1.0533266067504883,
+      "learning_rate": 0.0002,
+      "loss": 0.4284,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.8213809132575989,
+      "learning_rate": 0.0002,
+      "loss": 0.4414,
+      "step": 3080
+    },
+    {
+      "epoch": 3.796068796068796,
+      "grad_norm": 0.8941594362258911,
+      "learning_rate": 0.0002,
+      "loss": 0.4348,
+      "step": 3090
+    },
+    {
+      "epoch": 3.808353808353808,
+      "grad_norm": 0.8324518203735352,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 3100
+    },
+    {
+      "epoch": 3.8206388206388207,
+      "grad_norm": 0.8811233639717102,
+      "learning_rate": 0.0002,
+      "loss": 0.4227,
+      "step": 3110
+    },
+    {
+      "epoch": 3.832923832923833,
+      "grad_norm": 0.8781470060348511,
+      "learning_rate": 0.0002,
+      "loss": 0.4195,
+      "step": 3120
+    },
+    {
+      "epoch": 3.845208845208845,
+      "grad_norm": 0.8994116187095642,
+      "learning_rate": 0.0002,
+      "loss": 0.4277,
+      "step": 3130
+    },
+    {
+      "epoch": 3.8574938574938575,
+      "grad_norm": 0.8605017066001892,
+      "learning_rate": 0.0002,
+      "loss": 0.4149,
+      "step": 3140
+    },
+    {
+      "epoch": 3.8697788697788695,
+      "grad_norm": 0.8966400027275085,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 3150
+    },
+    {
+      "epoch": 3.882063882063882,
+      "grad_norm": 0.8856554627418518,
+      "learning_rate": 0.0002,
+      "loss": 0.4245,
+      "step": 3160
+    },
+    {
+      "epoch": 3.8943488943488944,
+      "grad_norm": 0.8971620798110962,
+      "learning_rate": 0.0002,
+      "loss": 0.4101,
+      "step": 3170
+    },
+    {
+      "epoch": 3.906633906633907,
+      "grad_norm": 0.9807813167572021,
+      "learning_rate": 0.0002,
+      "loss": 0.3993,
+      "step": 3180
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.8614121675491333,
+      "learning_rate": 0.0002,
+      "loss": 0.4258,
+      "step": 3190
+    },
+    {
+      "epoch": 3.9312039312039313,
+      "grad_norm": 0.989171028137207,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9434889434889433,
+      "grad_norm": 0.8168872594833374,
+      "learning_rate": 0.0002,
+      "loss": 0.4182,
+      "step": 3210
+    },
+    {
+      "epoch": 3.9557739557739557,
+      "grad_norm": 0.8109386563301086,
+      "learning_rate": 0.0002,
+      "loss": 0.4112,
+      "step": 3220
+    },
+    {
+      "epoch": 3.968058968058968,
+      "grad_norm": 1.0175853967666626,
+      "learning_rate": 0.0002,
+      "loss": 0.4165,
+      "step": 3230
+    },
+    {
+      "epoch": 3.98034398034398,
+      "grad_norm": 0.936143159866333,
+      "learning_rate": 0.0002,
+      "loss": 0.4146,
+      "step": 3240
+    },
+    {
+      "epoch": 3.9926289926289926,
+      "grad_norm": 0.9557915925979614,
+      "learning_rate": 0.0002,
+      "loss": 0.4163,
+      "step": 3250
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.4401616156101227,
+      "eval_runtime": 20.8047,
+      "eval_samples_per_second": 15.91,
+      "eval_steps_per_second": 2.019,
+      "step": 3256
+    },
+    {
+      "epoch": 4.004914004914005,
+      "grad_norm": 0.7590614557266235,
+      "learning_rate": 0.0002,
+      "loss": 0.408,
+      "step": 3260
+    },
+    {
+      "epoch": 4.017199017199017,
+      "grad_norm": 0.8920791149139404,
+      "learning_rate": 0.0002,
+      "loss": 0.4001,
+      "step": 3270
+    },
+    {
+      "epoch": 4.0294840294840295,
+      "grad_norm": 0.8640421628952026,
+      "learning_rate": 0.0002,
+      "loss": 0.3789,
+      "step": 3280
+    },
+    {
+      "epoch": 4.041769041769042,
+      "grad_norm": 0.9074113965034485,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3290
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 1.0600885152816772,
+      "learning_rate": 0.0002,
+      "loss": 0.3728,
+      "step": 3300
+    },
+    {
+      "epoch": 4.066339066339066,
+      "grad_norm": 0.9682773351669312,
+      "learning_rate": 0.0002,
+      "loss": 0.3857,
+      "step": 3310
+    },
+    {
+      "epoch": 4.078624078624078,
+      "grad_norm": 0.9326395392417908,
+      "learning_rate": 0.0002,
+      "loss": 0.4007,
+      "step": 3320
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.8886597156524658,
+      "learning_rate": 0.0002,
+      "loss": 0.3823,
+      "step": 3330
+    },
+    {
+      "epoch": 4.103194103194103,
+      "grad_norm": 1.032205581665039,
+      "learning_rate": 0.0002,
+      "loss": 0.3929,
+      "step": 3340
+    },
+    {
+      "epoch": 4.115479115479116,
+      "grad_norm": 0.8669408559799194,
+      "learning_rate": 0.0002,
+      "loss": 0.3836,
+      "step": 3350
+    },
+    {
+      "epoch": 4.127764127764128,
+      "grad_norm": 0.8250347971916199,
+      "learning_rate": 0.0002,
+      "loss": 0.3866,
+      "step": 3360
+    },
+    {
+      "epoch": 4.14004914004914,
+      "grad_norm": 0.7919842600822449,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3370
+    },
+    {
+      "epoch": 4.152334152334152,
+      "grad_norm": 1.045682430267334,
+      "learning_rate": 0.0002,
+      "loss": 0.3838,
+      "step": 3380
+    },
+    {
+      "epoch": 4.164619164619165,
+      "grad_norm": 0.6873571276664734,
+      "learning_rate": 0.0002,
+      "loss": 0.3796,
+      "step": 3390
+    },
+    {
+      "epoch": 4.176904176904177,
+      "grad_norm": 1.0227675437927246,
+      "learning_rate": 0.0002,
+      "loss": 0.3942,
+      "step": 3400
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 0.9167711734771729,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 3410
+    },
+    {
+      "epoch": 4.201474201474202,
+      "grad_norm": 1.0598796606063843,
+      "learning_rate": 0.0002,
+      "loss": 0.3792,
+      "step": 3420
+    },
+    {
+      "epoch": 4.2137592137592135,
+      "grad_norm": 0.8581843972206116,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3430
+    },
+    {
+      "epoch": 4.226044226044226,
+      "grad_norm": 0.8862360119819641,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3440
+    },
+    {
+      "epoch": 4.238329238329238,
+      "grad_norm": 1.0248323678970337,
+      "learning_rate": 0.0002,
+      "loss": 0.3889,
+      "step": 3450
+    },
+    {
+      "epoch": 4.250614250614251,
+      "grad_norm": 0.8746261596679688,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3460
+    },
+    {
+      "epoch": 4.262899262899263,
+      "grad_norm": 0.7442536354064941,
+      "learning_rate": 0.0002,
+      "loss": 0.3949,
+      "step": 3470
+    },
+    {
+      "epoch": 4.275184275184275,
+      "grad_norm": 0.8295119404792786,
+      "learning_rate": 0.0002,
+      "loss": 0.3761,
+      "step": 3480
+    },
+    {
+      "epoch": 4.287469287469287,
+      "grad_norm": 1.0634245872497559,
+      "learning_rate": 0.0002,
+      "loss": 0.3895,
+      "step": 3490
+    },
+    {
+      "epoch": 4.2997542997543,
+      "grad_norm": 0.9554621577262878,
+      "learning_rate": 0.0002,
+      "loss": 0.3955,
+      "step": 3500
+    },
+    {
+      "epoch": 4.312039312039312,
+      "grad_norm": 1.0191723108291626,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 3510
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.8573611378669739,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 3520
+    },
+    {
+      "epoch": 4.336609336609337,
+      "grad_norm": 0.9082390069961548,
+      "learning_rate": 0.0002,
+      "loss": 0.3869,
+      "step": 3530
+    },
+    {
+      "epoch": 4.348894348894349,
+      "grad_norm": 0.8650212287902832,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3540
+    },
+    {
+      "epoch": 4.361179361179361,
+      "grad_norm": 0.7186297178268433,
+      "learning_rate": 0.0002,
+      "loss": 0.3915,
+      "step": 3550
+    },
+    {
+      "epoch": 4.3734643734643734,
+      "grad_norm": 0.9750986695289612,
+      "learning_rate": 0.0002,
+      "loss": 0.3861,
+      "step": 3560
+    },
+    {
+      "epoch": 4.385749385749386,
+      "grad_norm": 1.0710467100143433,
+      "learning_rate": 0.0002,
+      "loss": 0.3967,
+      "step": 3570
+    },
+    {
+      "epoch": 4.398034398034398,
+      "grad_norm": 0.7974869012832642,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3580
+    },
+    {
+      "epoch": 4.41031941031941,
+      "grad_norm": 0.9405913949012756,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3590
+    },
+    {
+      "epoch": 4.422604422604422,
+      "grad_norm": 0.9393602609634399,
+      "learning_rate": 0.0002,
+      "loss": 0.3982,
+      "step": 3600
+    },
+    {
+      "epoch": 4.434889434889435,
+      "grad_norm": 1.0798007249832153,
+      "learning_rate": 0.0002,
+      "loss": 0.3913,
+      "step": 3610
+    },
+    {
+      "epoch": 4.447174447174447,
+      "grad_norm": 0.9226186275482178,
+      "learning_rate": 0.0002,
+      "loss": 0.3682,
+      "step": 3620
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 1.1046524047851562,
+      "learning_rate": 0.0002,
+      "loss": 0.3742,
+      "step": 3630
+    },
+    {
+      "epoch": 4.471744471744472,
+      "grad_norm": 0.8848567605018616,
+      "learning_rate": 0.0002,
+      "loss": 0.3886,
+      "step": 3640
+    },
+    {
+      "epoch": 4.484029484029484,
+      "grad_norm": 0.8913224339485168,
+      "learning_rate": 0.0002,
+      "loss": 0.3848,
+      "step": 3650
+    },
+    {
+      "epoch": 4.496314496314496,
+      "grad_norm": 0.8497583270072937,
+      "learning_rate": 0.0002,
+      "loss": 0.3731,
+      "step": 3660
+    },
+    {
+      "epoch": 4.5085995085995085,
+      "grad_norm": 0.8263831734657288,
+      "learning_rate": 0.0002,
+      "loss": 0.3804,
+      "step": 3670
+    },
+    {
+      "epoch": 4.520884520884521,
+      "grad_norm": 0.8470269441604614,
+      "learning_rate": 0.0002,
+      "loss": 0.3815,
+      "step": 3680
+    },
+    {
+      "epoch": 4.533169533169533,
+      "grad_norm": 0.860038161277771,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 3690
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.8898552656173706,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3700
+    },
+    {
+      "epoch": 4.557739557739557,
+      "grad_norm": 0.8152070641517639,
+      "learning_rate": 0.0002,
+      "loss": 0.3776,
+      "step": 3710
+    },
+    {
+      "epoch": 4.57002457002457,
+      "grad_norm": 0.7847675085067749,
+      "learning_rate": 0.0002,
+      "loss": 0.383,
+      "step": 3720
+    },
+    {
+      "epoch": 4.582309582309582,
+      "grad_norm": 0.9625533819198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3791,
+      "step": 3730
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.9097456336021423,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 3740
+    },
+    {
+      "epoch": 4.606879606879607,
+      "grad_norm": 0.871329128742218,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 3750
+    },
+    {
+      "epoch": 4.61916461916462,
+      "grad_norm": 0.9879975914955139,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 3760
+    },
+    {
+      "epoch": 4.631449631449631,
+      "grad_norm": 0.8636731505393982,
+      "learning_rate": 0.0002,
+      "loss": 0.3827,
+      "step": 3770
+    },
+    {
+      "epoch": 4.643734643734644,
+      "grad_norm": 1.0488964319229126,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 3780
+    },
+    {
+      "epoch": 4.656019656019656,
+      "grad_norm": 0.7637056112289429,
+      "learning_rate": 0.0002,
+      "loss": 0.3738,
+      "step": 3790
+    },
+    {
+      "epoch": 4.6683046683046685,
+      "grad_norm": 0.8507546186447144,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 3800
+    },
+    {
+      "epoch": 4.680589680589681,
+      "grad_norm": 1.0216856002807617,
+      "learning_rate": 0.0002,
+      "loss": 0.3852,
+      "step": 3810
+    },
+    {
+      "epoch": 4.6928746928746925,
+      "grad_norm": 1.026343822479248,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 3820
+    },
+    {
+      "epoch": 4.705159705159705,
+      "grad_norm": 0.8311620950698853,
+      "learning_rate": 0.0002,
+      "loss": 0.3687,
+      "step": 3830
+    },
+    {
+      "epoch": 4.717444717444717,
+      "grad_norm": 0.7770653367042542,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 3840
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 0.7616215348243713,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3850
+    },
+    {
+      "epoch": 4.742014742014742,
+      "grad_norm": 1.0377072095870972,
+      "learning_rate": 0.0002,
+      "loss": 0.3927,
+      "step": 3860
+    },
+    {
+      "epoch": 4.754299754299755,
+      "grad_norm": 0.9713505506515503,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 3870
+    },
+    {
+      "epoch": 4.766584766584766,
+      "grad_norm": 0.8803321719169617,
+      "learning_rate": 0.0002,
+      "loss": 0.3722,
+      "step": 3880
+    },
+    {
+      "epoch": 4.778869778869779,
+      "grad_norm": 0.885535478591919,
+      "learning_rate": 0.0002,
+      "loss": 0.3756,
+      "step": 3890
+    },
+    {
+      "epoch": 4.791154791154791,
+      "grad_norm": 1.0877983570098877,
+      "learning_rate": 0.0002,
+      "loss": 0.3714,
+      "step": 3900
+    },
+    {
+      "epoch": 4.803439803439804,
+      "grad_norm": 0.7875366806983948,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3910
+    },
+    {
+      "epoch": 4.815724815724816,
+      "grad_norm": 0.8550102114677429,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 3920
+    },
+    {
+      "epoch": 4.828009828009828,
+      "grad_norm": 1.0217846632003784,
+      "learning_rate": 0.0002,
+      "loss": 0.3716,
+      "step": 3930
+    },
+    {
+      "epoch": 4.84029484029484,
+      "grad_norm": 0.7315713167190552,
+      "learning_rate": 0.0002,
+      "loss": 0.3649,
+      "step": 3940
+    },
+    {
+      "epoch": 4.8525798525798525,
+      "grad_norm": 0.8924923539161682,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 3950
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 0.9730218052864075,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 3960
+    },
+    {
+      "epoch": 4.877149877149877,
+      "grad_norm": 0.9202003479003906,
+      "learning_rate": 0.0002,
+      "loss": 0.3705,
+      "step": 3970
+    },
+    {
+      "epoch": 4.88943488943489,
+      "grad_norm": 0.8173081874847412,
+      "learning_rate": 0.0002,
+      "loss": 0.3617,
+      "step": 3980
+    },
+    {
+      "epoch": 4.901719901719901,
+      "grad_norm": 0.7178564667701721,
+      "learning_rate": 0.0002,
+      "loss": 0.37,
+      "step": 3990
+    },
+    {
+      "epoch": 4.914004914004914,
+      "grad_norm": 0.913684606552124,
+      "learning_rate": 0.0002,
+      "loss": 0.3768,
+      "step": 4000
+    },
+    {
+      "epoch": 4.926289926289926,
+      "grad_norm": 0.8817896842956543,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 4010
+    },
+    {
+      "epoch": 4.938574938574939,
+      "grad_norm": 0.7652186751365662,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 4020
+    },
+    {
+      "epoch": 4.950859950859951,
+      "grad_norm": 0.8828630447387695,
+      "learning_rate": 0.0002,
+      "loss": 0.3699,
+      "step": 4030
+    },
+    {
+      "epoch": 4.963144963144963,
+      "grad_norm": 1.0878605842590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3672,
+      "step": 4040
+    },
+    {
+      "epoch": 4.975429975429975,
+      "grad_norm": 1.0845288038253784,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 4050
+    },
+    {
+      "epoch": 4.987714987714988,
+      "grad_norm": 0.8431115746498108,
+      "learning_rate": 0.0002,
+      "loss": 0.365,
+      "step": 4060
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8320387601852417,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4070
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.4017423093318939,
+      "eval_runtime": 20.8466,
+      "eval_samples_per_second": 15.878,
+      "eval_steps_per_second": 2.015,
+      "step": 4070
+    },
+    {
+      "epoch": 5.012285012285012,
+      "grad_norm": 0.8639023900032043,
+      "learning_rate": 0.0002,
+      "loss": 0.3425,
+      "step": 4080
+    },
+    {
+      "epoch": 5.024570024570025,
+      "grad_norm": 0.7123713493347168,
+      "learning_rate": 0.0002,
+      "loss": 0.3458,
+      "step": 4090
+    },
+    {
+      "epoch": 5.036855036855036,
+      "grad_norm": 0.9886922836303711,
+      "learning_rate": 0.0002,
+      "loss": 0.3404,
+      "step": 4100
+    },
+    {
+      "epoch": 5.049140049140049,
+      "grad_norm": 0.7880306243896484,
+      "learning_rate": 0.0002,
+      "loss": 0.3529,
+      "step": 4110
+    },
+    {
+      "epoch": 5.061425061425061,
+      "grad_norm": 0.7488741874694824,
+      "learning_rate": 0.0002,
+      "loss": 0.3406,
+      "step": 4120
+    },
+    {
+      "epoch": 5.073710073710074,
+      "grad_norm": 0.9359086751937866,
+      "learning_rate": 0.0002,
+      "loss": 0.3542,
+      "step": 4130
+    },
+    {
+      "epoch": 5.085995085995086,
+      "grad_norm": 0.9401527047157288,
+      "learning_rate": 0.0002,
+      "loss": 0.3471,
+      "step": 4140
+    },
+    {
+      "epoch": 5.098280098280099,
+      "grad_norm": 0.8396275043487549,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 4150
+    },
+    {
+      "epoch": 5.11056511056511,
+      "grad_norm": 0.7132664918899536,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4160
+    },
+    {
+      "epoch": 5.122850122850123,
+      "grad_norm": 0.843708872795105,
+      "learning_rate": 0.0002,
+      "loss": 0.3457,
+      "step": 4170
+    },
+    {
+      "epoch": 5.135135135135135,
+      "grad_norm": 0.8733304738998413,
+      "learning_rate": 0.0002,
+      "loss": 0.3399,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1474201474201475,
+      "grad_norm": 0.9064375162124634,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4190
+    },
+    {
+      "epoch": 5.15970515970516,
+      "grad_norm": 0.900770902633667,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4200
+    },
+    {
+      "epoch": 5.171990171990172,
+      "grad_norm": 0.863853394985199,
+      "learning_rate": 0.0002,
+      "loss": 0.3475,
+      "step": 4210
+    },
+    {
+      "epoch": 5.184275184275184,
+      "grad_norm": 0.767134964466095,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 4220
+    },
+    {
+      "epoch": 5.196560196560196,
+      "grad_norm": 0.7518735527992249,
+      "learning_rate": 0.0002,
+      "loss": 0.3527,
+      "step": 4230
+    },
+    {
+      "epoch": 5.208845208845209,
+      "grad_norm": 0.8040947914123535,
+      "learning_rate": 0.0002,
+      "loss": 0.3369,
+      "step": 4240
+    },
+    {
+      "epoch": 5.221130221130221,
+      "grad_norm": 0.7827144265174866,
+      "learning_rate": 0.0002,
+      "loss": 0.3496,
+      "step": 4250
+    },
+    {
+      "epoch": 5.233415233415234,
+      "grad_norm": 0.7306333184242249,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4260
+    },
+    {
+      "epoch": 5.245700245700245,
+      "grad_norm": 1.0963380336761475,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4270
+    },
+    {
+      "epoch": 5.257985257985258,
+      "grad_norm": 0.8200454711914062,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4280
+    },
+    {
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.8666796684265137,
+      "learning_rate": 0.0002,
+      "loss": 0.3509,
+      "step": 4290
+    },
+    {
+      "epoch": 5.282555282555283,
+      "grad_norm": 0.7862894535064697,
+      "learning_rate": 0.0002,
+      "loss": 0.3423,
+      "step": 4300
+    },
+    {
+      "epoch": 5.294840294840295,
+      "grad_norm": 0.8163095712661743,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4310
+    },
+    {
+      "epoch": 5.3071253071253075,
+      "grad_norm": 0.8069050908088684,
+      "learning_rate": 0.0002,
+      "loss": 0.34,
+      "step": 4320
+    },
+    {
+      "epoch": 5.319410319410319,
+      "grad_norm": 0.7858486175537109,
+      "learning_rate": 0.0002,
+      "loss": 0.3532,
+      "step": 4330
+    },
+    {
+      "epoch": 5.3316953316953315,
+      "grad_norm": 0.950339674949646,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4340
+    },
+    {
+      "epoch": 5.343980343980344,
+      "grad_norm": 0.9056477546691895,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4350
+    },
+    {
+      "epoch": 5.356265356265356,
+      "grad_norm": 0.9619399905204773,
+      "learning_rate": 0.0002,
+      "loss": 0.3538,
+      "step": 4360
+    },
+    {
+      "epoch": 5.368550368550369,
+      "grad_norm": 0.9778652191162109,
+      "learning_rate": 0.0002,
+      "loss": 0.3455,
+      "step": 4370
+    },
+    {
+      "epoch": 5.38083538083538,
+      "grad_norm": 0.6919555068016052,
+      "learning_rate": 0.0002,
+      "loss": 0.3498,
+      "step": 4380
+    },
+    {
+      "epoch": 5.393120393120393,
+      "grad_norm": 0.8121668696403503,
+      "learning_rate": 0.0002,
+      "loss": 0.3426,
+      "step": 4390
+    },
+    {
+      "epoch": 5.405405405405405,
+      "grad_norm": 0.8481289148330688,
+      "learning_rate": 0.0002,
+      "loss": 0.3442,
+      "step": 4400
+    },
+    {
+      "epoch": 5.417690417690418,
+      "grad_norm": 0.8727408647537231,
+      "learning_rate": 0.0002,
+      "loss": 0.345,
+      "step": 4410
+    },
+    {
+      "epoch": 5.42997542997543,
+      "grad_norm": 0.8920271396636963,
+      "learning_rate": 0.0002,
+      "loss": 0.3554,
+      "step": 4420
+    },
+    {
+      "epoch": 5.442260442260443,
+      "grad_norm": 0.7758749723434448,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4430
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.8847506642341614,
+      "learning_rate": 0.0002,
+      "loss": 0.3483,
+      "step": 4440
+    },
+    {
+      "epoch": 5.466830466830467,
+      "grad_norm": 0.9760470390319824,
+      "learning_rate": 0.0002,
+      "loss": 0.3557,
+      "step": 4450
+    },
+    {
+      "epoch": 5.479115479115479,
+      "grad_norm": 0.8940271139144897,
+      "learning_rate": 0.0002,
+      "loss": 0.3536,
+      "step": 4460
+    },
+    {
+      "epoch": 5.4914004914004915,
+      "grad_norm": 0.8668502569198608,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 4470
+    },
+    {
+      "epoch": 5.503685503685504,
+      "grad_norm": 0.9097439050674438,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4480
+    },
+    {
+      "epoch": 5.515970515970516,
+      "grad_norm": 0.8217208981513977,
+      "learning_rate": 0.0002,
+      "loss": 0.3417,
+      "step": 4490
+    },
+    {
+      "epoch": 5.528255528255528,
+      "grad_norm": 0.7853189706802368,
+      "learning_rate": 0.0002,
+      "loss": 0.3482,
+      "step": 4500
+    },
+    {
+      "epoch": 5.54054054054054,
+      "grad_norm": 1.1113477945327759,
+      "learning_rate": 0.0002,
+      "loss": 0.3479,
+      "step": 4510
+    },
+    {
+      "epoch": 5.552825552825553,
+      "grad_norm": 0.8637538552284241,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 4520
+    },
+    {
+      "epoch": 5.565110565110565,
+      "grad_norm": 1.0230066776275635,
+      "learning_rate": 0.0002,
+      "loss": 0.3403,
+      "step": 4530
+    },
+    {
+      "epoch": 5.577395577395578,
+      "grad_norm": 0.8972793817520142,
+      "learning_rate": 0.0002,
+      "loss": 0.3588,
+      "step": 4540
+    },
+    {
+      "epoch": 5.58968058968059,
+      "grad_norm": 0.7950642704963684,
+      "learning_rate": 0.0002,
+      "loss": 0.3428,
+      "step": 4550
+    },
+    {
+      "epoch": 5.601965601965602,
+      "grad_norm": 1.113753318786621,
+      "learning_rate": 0.0002,
+      "loss": 0.3468,
+      "step": 4560
+    },
+    {
+      "epoch": 5.614250614250614,
+      "grad_norm": 0.7842669486999512,
+      "learning_rate": 0.0002,
+      "loss": 0.3354,
+      "step": 4570
+    },
+    {
+      "epoch": 5.6265356265356266,
+      "grad_norm": 0.9713512063026428,
+      "learning_rate": 0.0002,
+      "loss": 0.3419,
+      "step": 4580
+    },
+    {
+      "epoch": 5.638820638820639,
+      "grad_norm": 0.9451650977134705,
+      "learning_rate": 0.0002,
+      "loss": 0.3502,
+      "step": 4590
+    },
+    {
+      "epoch": 5.651105651105651,
+      "grad_norm": 1.055484414100647,
+      "learning_rate": 0.0002,
+      "loss": 0.3416,
+      "step": 4600
+    },
+    {
+      "epoch": 5.663390663390663,
+      "grad_norm": 0.8408507704734802,
+      "learning_rate": 0.0002,
+      "loss": 0.3436,
+      "step": 4610
+    },
+    {
+      "epoch": 5.675675675675675,
+      "grad_norm": 1.0293926000595093,
+      "learning_rate": 0.0002,
+      "loss": 0.3619,
+      "step": 4620
+    },
+    {
+      "epoch": 5.687960687960688,
+      "grad_norm": 0.7198245525360107,
+      "learning_rate": 0.0002,
+      "loss": 0.3484,
+      "step": 4630
+    },
+    {
+      "epoch": 5.7002457002457,
+      "grad_norm": 0.7564466595649719,
+      "learning_rate": 0.0002,
+      "loss": 0.3563,
+      "step": 4640
+    },
+    {
+      "epoch": 5.712530712530713,
+      "grad_norm": 0.7980002760887146,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4650
+    },
+    {
+      "epoch": 5.724815724815725,
+      "grad_norm": 0.8685088753700256,
+      "learning_rate": 0.0002,
+      "loss": 0.3478,
+      "step": 4660
+    },
+    {
+      "epoch": 5.737100737100737,
+      "grad_norm": 0.8816949129104614,
+      "learning_rate": 0.0002,
+      "loss": 0.3692,
+      "step": 4670
+    },
+    {
+      "epoch": 5.749385749385749,
+      "grad_norm": 0.7154731750488281,
+      "learning_rate": 0.0002,
+      "loss": 0.3462,
+      "step": 4680
+    },
+    {
+      "epoch": 5.761670761670762,
+      "grad_norm": 0.9430679678916931,
+      "learning_rate": 0.0002,
+      "loss": 0.3503,
+      "step": 4690
+    },
+    {
+      "epoch": 5.773955773955774,
+      "grad_norm": 0.7640151381492615,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4700
+    },
+    {
+      "epoch": 5.7862407862407865,
+      "grad_norm": 1.0920690298080444,
+      "learning_rate": 0.0002,
+      "loss": 0.3444,
+      "step": 4710
+    },
+    {
+      "epoch": 5.798525798525798,
+      "grad_norm": 0.9362104535102844,
+      "learning_rate": 0.0002,
+      "loss": 0.3356,
+      "step": 4720
+    },
+    {
+      "epoch": 5.8108108108108105,
+      "grad_norm": 0.8392294645309448,
+      "learning_rate": 0.0002,
+      "loss": 0.339,
+      "step": 4730
+    },
+    {
+      "epoch": 5.823095823095823,
+      "grad_norm": 0.9893582463264465,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 4740
+    },
+    {
+      "epoch": 5.835380835380835,
+      "grad_norm": 0.6985510587692261,
+      "learning_rate": 0.0002,
+      "loss": 0.3446,
+      "step": 4750
+    },
+    {
+      "epoch": 5.847665847665848,
+      "grad_norm": 0.8906862735748291,
+      "learning_rate": 0.0002,
+      "loss": 0.3534,
+      "step": 4760
+    },
+    {
+      "epoch": 5.85995085995086,
+      "grad_norm": 0.8036413192749023,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 4770
+    },
+    {
+      "epoch": 5.872235872235873,
+      "grad_norm": 0.9948155283927917,
+      "learning_rate": 0.0002,
+      "loss": 0.3326,
+      "step": 4780
+    },
+    {
+      "epoch": 5.884520884520884,
+      "grad_norm": 0.8618432283401489,
+      "learning_rate": 0.0002,
+      "loss": 0.3385,
+      "step": 4790
+    },
+    {
+      "epoch": 5.896805896805897,
+      "grad_norm": 1.0422909259796143,
+      "learning_rate": 0.0002,
+      "loss": 0.3302,
+      "step": 4800
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 1.1892569065093994,
+      "learning_rate": 0.0002,
+      "loss": 0.3448,
+      "step": 4810
+    },
+    {
+      "epoch": 5.921375921375922,
+      "grad_norm": 1.1459916830062866,
+      "learning_rate": 0.0002,
+      "loss": 0.3506,
+      "step": 4820
+    },
+    {
+      "epoch": 5.933660933660933,
+      "grad_norm": 1.056235909461975,
+      "learning_rate": 0.0002,
+      "loss": 0.3387,
+      "step": 4830
+    },
+    {
+      "epoch": 5.945945945945946,
+      "grad_norm": 0.8517277240753174,
+      "learning_rate": 0.0002,
+      "loss": 0.344,
+      "step": 4840
+    },
+    {
+      "epoch": 5.958230958230958,
+      "grad_norm": 0.8153380751609802,
+      "learning_rate": 0.0002,
+      "loss": 0.3421,
+      "step": 4850
+    },
+    {
+      "epoch": 5.9705159705159705,
+      "grad_norm": 0.7907533049583435,
+      "learning_rate": 0.0002,
+      "loss": 0.3409,
+      "step": 4860
+    },
+    {
+      "epoch": 5.982800982800983,
+      "grad_norm": 0.8443069458007812,
+      "learning_rate": 0.0002,
+      "loss": 0.3337,
+      "step": 4870
+    },
+    {
+      "epoch": 5.995085995085995,
+      "grad_norm": 0.8711344003677368,
+      "learning_rate": 0.0002,
+      "loss": 0.3351,
+      "step": 4880
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.3778059184551239,
+      "eval_runtime": 20.6858,
+      "eval_samples_per_second": 16.001,
+      "eval_steps_per_second": 2.03,
+      "step": 4884
+    },
+    {
+      "epoch": 6.007371007371007,
+      "grad_norm": 0.7697948813438416,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 4890
+    },
+    {
+      "epoch": 6.019656019656019,
+      "grad_norm": 0.7734108567237854,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 4900
+    },
+    {
+      "epoch": 6.031941031941032,
+      "grad_norm": 0.7173922657966614,
+      "learning_rate": 0.0002,
+      "loss": 0.3242,
+      "step": 4910
+    },
+    {
+      "epoch": 6.044226044226044,
+      "grad_norm": 1.062118649482727,
+      "learning_rate": 0.0002,
+      "loss": 0.3159,
+      "step": 4920
+    },
+    {
+      "epoch": 6.056511056511057,
+      "grad_norm": 0.746422529220581,
+      "learning_rate": 0.0002,
+      "loss": 0.3361,
+      "step": 4930
+    },
+    {
+      "epoch": 6.068796068796069,
+      "grad_norm": 0.8549448251724243,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 4940
+    },
+    {
+      "epoch": 6.081081081081081,
+      "grad_norm": 0.9405432939529419,
+      "learning_rate": 0.0002,
+      "loss": 0.3236,
+      "step": 4950
+    },
+    {
+      "epoch": 6.093366093366093,
+      "grad_norm": 0.752382755279541,
+      "learning_rate": 0.0002,
+      "loss": 0.3278,
+      "step": 4960
+    },
+    {
+      "epoch": 6.105651105651106,
+      "grad_norm": 0.820332407951355,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 4970
+    },
+    {
+      "epoch": 6.117936117936118,
+      "grad_norm": 0.8701449036598206,
+      "learning_rate": 0.0002,
+      "loss": 0.3192,
+      "step": 4980
+    },
+    {
+      "epoch": 6.1302211302211305,
+      "grad_norm": 0.8192865252494812,
+      "learning_rate": 0.0002,
+      "loss": 0.321,
+      "step": 4990
+    },
+    {
+      "epoch": 6.142506142506143,
+      "grad_norm": 1.0016303062438965,
+      "learning_rate": 0.0002,
+      "loss": 0.3295,
+      "step": 5000
+    },
+    {
+      "epoch": 6.1547911547911545,
+      "grad_norm": 0.9194409251213074,
+      "learning_rate": 0.0002,
+      "loss": 0.3352,
+      "step": 5010
+    },
+    {
+      "epoch": 6.167076167076167,
+      "grad_norm": 0.9319757223129272,
+      "learning_rate": 0.0002,
+      "loss": 0.3205,
+      "step": 5020
+    },
+    {
+      "epoch": 6.179361179361179,
+      "grad_norm": 0.8737656474113464,
+      "learning_rate": 0.0002,
+      "loss": 0.3256,
+      "step": 5030
+    },
+    {
+      "epoch": 6.191646191646192,
+      "grad_norm": 0.8736537098884583,
+      "learning_rate": 0.0002,
+      "loss": 0.3221,
+      "step": 5040
+    },
+    {
+      "epoch": 6.203931203931204,
+      "grad_norm": 0.9301430583000183,
+      "learning_rate": 0.0002,
+      "loss": 0.3265,
+      "step": 5050
+    },
+    {
+      "epoch": 6.216216216216216,
+      "grad_norm": 0.7717130780220032,
+      "learning_rate": 0.0002,
+      "loss": 0.3285,
+      "step": 5060
+    },
+    {
+      "epoch": 6.228501228501228,
+      "grad_norm": 0.6709604859352112,
+      "learning_rate": 0.0002,
+      "loss": 0.3192,
+      "step": 5070
+    },
+    {
+      "epoch": 6.240786240786241,
+      "grad_norm": 0.879374086856842,
+      "learning_rate": 0.0002,
+      "loss": 0.3352,
+      "step": 5080
+    },
+    {
+      "epoch": 6.253071253071253,
+      "grad_norm": 0.9136955738067627,
+      "learning_rate": 0.0002,
+      "loss": 0.329,
+      "step": 5090
+    },
+    {
+      "epoch": 6.2653562653562656,
+      "grad_norm": 0.795177161693573,
+      "learning_rate": 0.0002,
+      "loss": 0.3228,
+      "step": 5100
+    },
+    {
+      "epoch": 6.277641277641278,
+      "grad_norm": 1.0412259101867676,
+      "learning_rate": 0.0002,
+      "loss": 0.3273,
+      "step": 5110
+    },
+    {
+      "epoch": 6.2899262899262895,
+      "grad_norm": 0.7382524013519287,
+      "learning_rate": 0.0002,
+      "loss": 0.3221,
+      "step": 5120
+    },
+    {
+      "epoch": 6.302211302211302,
+      "grad_norm": 0.8818480968475342,
+      "learning_rate": 0.0002,
+      "loss": 0.3102,
+      "step": 5130
+    },
+    {
+      "epoch": 6.314496314496314,
+      "grad_norm": 0.7865153551101685,
+      "learning_rate": 0.0002,
+      "loss": 0.3316,
+      "step": 5140
+    },
+    {
+      "epoch": 6.326781326781327,
+      "grad_norm": 0.9166486859321594,
+      "learning_rate": 0.0002,
+      "loss": 0.3264,
+      "step": 5150
+    },
+    {
+      "epoch": 6.339066339066339,
+      "grad_norm": 0.6655149459838867,
+      "learning_rate": 0.0002,
+      "loss": 0.33,
+      "step": 5160
+    },
+    {
+      "epoch": 6.351351351351352,
+      "grad_norm": 0.7762818336486816,
+      "learning_rate": 0.0002,
+      "loss": 0.3359,
+      "step": 5170
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.8057235479354858,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 5180
+    },
+    {
+      "epoch": 6.375921375921376,
+      "grad_norm": 0.8186984062194824,
+      "learning_rate": 0.0002,
+      "loss": 0.3167,
+      "step": 5190
+    },
+    {
+      "epoch": 6.388206388206388,
+      "grad_norm": 0.8669573068618774,
+      "learning_rate": 0.0002,
+      "loss": 0.3289,
+      "step": 5200
+    },
+    {
+      "epoch": 6.400491400491401,
+      "grad_norm": 0.8904402852058411,
+      "learning_rate": 0.0002,
+      "loss": 0.3313,
+      "step": 5210
+    },
+    {
+      "epoch": 6.412776412776413,
+      "grad_norm": 0.9250359535217285,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 5220
+    },
+    {
+      "epoch": 6.4250614250614255,
+      "grad_norm": 0.8718299269676208,
+      "learning_rate": 0.0002,
+      "loss": 0.3229,
+      "step": 5230
+    },
+    {
+      "epoch": 6.437346437346437,
+      "grad_norm": 0.8156430125236511,
+      "learning_rate": 0.0002,
+      "loss": 0.3214,
+      "step": 5240
+    },
+    {
+      "epoch": 6.4496314496314495,
+      "grad_norm": 0.7759218215942383,
+      "learning_rate": 0.0002,
+      "loss": 0.3244,
+      "step": 5250
+    },
+    {
+      "epoch": 6.461916461916462,
+      "grad_norm": 0.8137310743331909,
+      "learning_rate": 0.0002,
+      "loss": 0.3298,
+      "step": 5260
+    },
+    {
+      "epoch": 6.474201474201474,
+      "grad_norm": 0.8121917843818665,
+      "learning_rate": 0.0002,
+      "loss": 0.3275,
+      "step": 5270
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 0.8178010582923889,
+      "learning_rate": 0.0002,
+      "loss": 0.3201,
+      "step": 5280
+    },
+    {
+      "epoch": 6.498771498771498,
+      "grad_norm": 1.1806302070617676,
+      "learning_rate": 0.0002,
+      "loss": 0.3271,
+      "step": 5290
+    },
+    {
+      "epoch": 6.511056511056511,
+      "grad_norm": 0.8255127668380737,
+      "learning_rate": 0.0002,
+      "loss": 0.3231,
+      "step": 5300
+    },
+    {
+      "epoch": 6.523341523341523,
+      "grad_norm": 0.8006690740585327,
+      "learning_rate": 0.0002,
+      "loss": 0.3227,
+      "step": 5310
+    },
+    {
+      "epoch": 6.535626535626536,
+      "grad_norm": 0.9932374358177185,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 5320
+    },
+    {
+      "epoch": 6.547911547911548,
+      "grad_norm": 0.8973969221115112,
+      "learning_rate": 0.0002,
+      "loss": 0.3291,
+      "step": 5330
+    },
+    {
+      "epoch": 6.560196560196561,
+      "grad_norm": 0.7359915971755981,
+      "learning_rate": 0.0002,
+      "loss": 0.3146,
+      "step": 5340
+    },
+    {
+      "epoch": 6.572481572481572,
+      "grad_norm": 0.9941133856773376,
+      "learning_rate": 0.0002,
+      "loss": 0.3308,
+      "step": 5350
+    },
+    {
+      "epoch": 6.584766584766585,
+      "grad_norm": 0.9008874893188477,
+      "learning_rate": 0.0002,
+      "loss": 0.3202,
+      "step": 5360
+    },
+    {
+      "epoch": 6.597051597051597,
+      "grad_norm": 1.309710144996643,
+      "learning_rate": 0.0002,
+      "loss": 0.3271,
+      "step": 5370
+    },
+    {
+      "epoch": 6.6093366093366095,
+      "grad_norm": 0.797768235206604,
+      "learning_rate": 0.0002,
+      "loss": 0.3177,
+      "step": 5380
+    },
+    {
+      "epoch": 6.621621621621622,
+      "grad_norm": 0.8507353663444519,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5390
+    },
+    {
+      "epoch": 6.6339066339066335,
+      "grad_norm": 0.9628674983978271,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 5400
+    },
+    {
+      "epoch": 6.646191646191646,
+      "grad_norm": 0.6989983320236206,
+      "learning_rate": 0.0002,
+      "loss": 0.3155,
+      "step": 5410
+    },
+    {
+      "epoch": 6.658476658476658,
+      "grad_norm": 0.9505863189697266,
+      "learning_rate": 0.0002,
+      "loss": 0.3197,
+      "step": 5420
+    },
+    {
+      "epoch": 6.670761670761671,
+      "grad_norm": 0.8058171272277832,
+      "learning_rate": 0.0002,
+      "loss": 0.3259,
+      "step": 5430
+    },
+    {
+      "epoch": 6.683046683046683,
+      "grad_norm": 0.8476499915122986,
+      "learning_rate": 0.0002,
+      "loss": 0.3248,
+      "step": 5440
+    },
+    {
+      "epoch": 6.695331695331696,
+      "grad_norm": 0.8503309488296509,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 5450
+    },
+    {
+      "epoch": 6.707616707616707,
+      "grad_norm": 0.919566810131073,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5460
+    },
+    {
+      "epoch": 6.71990171990172,
+      "grad_norm": 0.7741201519966125,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 5470
+    },
+    {
+      "epoch": 6.732186732186732,
+      "grad_norm": 0.8432701826095581,
+      "learning_rate": 0.0002,
+      "loss": 0.329,
+      "step": 5480
+    },
+    {
+      "epoch": 6.744471744471745,
+      "grad_norm": 1.0183148384094238,
+      "learning_rate": 0.0002,
+      "loss": 0.3284,
+      "step": 5490
+    },
+    {
+      "epoch": 6.756756756756757,
+      "grad_norm": 0.8491143584251404,
+      "learning_rate": 0.0002,
+      "loss": 0.3312,
+      "step": 5500
+    },
+    {
+      "epoch": 6.769041769041769,
+      "grad_norm": 0.9586310386657715,
+      "learning_rate": 0.0002,
+      "loss": 0.3208,
+      "step": 5510
+    },
+    {
+      "epoch": 6.781326781326781,
+      "grad_norm": 0.7936097383499146,
+      "learning_rate": 0.0002,
+      "loss": 0.3305,
+      "step": 5520
+    },
+    {
+      "epoch": 6.7936117936117935,
+      "grad_norm": 0.7875059247016907,
+      "learning_rate": 0.0002,
+      "loss": 0.318,
+      "step": 5530
+    },
+    {
+      "epoch": 6.805896805896806,
+      "grad_norm": 0.8136157393455505,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 5540
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.837213933467865,
+      "learning_rate": 0.0002,
+      "loss": 0.3161,
+      "step": 5550
+    },
+    {
+      "epoch": 6.830466830466831,
+      "grad_norm": 0.6812925338745117,
+      "learning_rate": 0.0002,
+      "loss": 0.3153,
+      "step": 5560
+    },
+    {
+      "epoch": 6.842751842751843,
+      "grad_norm": 0.7309592962265015,
+      "learning_rate": 0.0002,
+      "loss": 0.3139,
+      "step": 5570
+    },
+    {
+      "epoch": 6.855036855036855,
+      "grad_norm": 0.6905979514122009,
+      "learning_rate": 0.0002,
+      "loss": 0.3126,
+      "step": 5580
+    },
+    {
+      "epoch": 6.867321867321867,
+      "grad_norm": 1.1768406629562378,
+      "learning_rate": 0.0002,
+      "loss": 0.3291,
+      "step": 5590
+    },
+    {
+      "epoch": 6.87960687960688,
+      "grad_norm": 0.7618567943572998,
+      "learning_rate": 0.0002,
+      "loss": 0.3193,
+      "step": 5600
+    },
+    {
+      "epoch": 6.891891891891892,
+      "grad_norm": 0.7930929660797119,
+      "learning_rate": 0.0002,
+      "loss": 0.3296,
+      "step": 5610
+    },
+    {
+      "epoch": 6.9041769041769046,
+      "grad_norm": 0.7931787371635437,
+      "learning_rate": 0.0002,
+      "loss": 0.3241,
+      "step": 5620
+    },
+    {
+      "epoch": 6.916461916461916,
+      "grad_norm": 0.6366972923278809,
+      "learning_rate": 0.0002,
+      "loss": 0.3215,
+      "step": 5630
+    },
+    {
+      "epoch": 6.9287469287469285,
+      "grad_norm": 0.7782737612724304,
+      "learning_rate": 0.0002,
+      "loss": 0.3264,
+      "step": 5640
+    },
+    {
+      "epoch": 6.941031941031941,
+      "grad_norm": 0.8643787503242493,
+      "learning_rate": 0.0002,
+      "loss": 0.3186,
+      "step": 5650
+    },
+    {
+      "epoch": 6.953316953316953,
+      "grad_norm": 1.0843733549118042,
+      "learning_rate": 0.0002,
+      "loss": 0.3285,
+      "step": 5660
+    },
+    {
+      "epoch": 6.965601965601966,
+      "grad_norm": 0.71319180727005,
+      "learning_rate": 0.0002,
+      "loss": 0.3163,
+      "step": 5670
+    },
+    {
+      "epoch": 6.977886977886978,
+      "grad_norm": 0.976536750793457,
+      "learning_rate": 0.0002,
+      "loss": 0.3196,
+      "step": 5680
+    },
+    {
+      "epoch": 6.99017199017199,
+      "grad_norm": 0.9221968054771423,
+      "learning_rate": 0.0002,
+      "loss": 0.3255,
+      "step": 5690
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.3616626560688019,
+      "eval_runtime": 20.8747,
+      "eval_samples_per_second": 15.857,
+      "eval_steps_per_second": 2.012,
+      "step": 5698
+    },
+    {
+      "epoch": 7.002457002457002,
+      "grad_norm": 0.6302434802055359,
+      "learning_rate": 0.0002,
+      "loss": 0.3149,
+      "step": 5700
+    },
+    {
+      "epoch": 7.014742014742015,
+      "grad_norm": 0.7077583074569702,
+      "learning_rate": 0.0002,
+      "loss": 0.3017,
+      "step": 5710
+    },
+    {
+      "epoch": 7.027027027027027,
+      "grad_norm": 0.7005309462547302,
+      "learning_rate": 0.0002,
+      "loss": 0.303,
+      "step": 5720
+    },
+    {
+      "epoch": 7.03931203931204,
+      "grad_norm": 0.7724815607070923,
+      "learning_rate": 0.0002,
+      "loss": 0.3069,
+      "step": 5730
+    },
+    {
+      "epoch": 7.051597051597051,
+      "grad_norm": 0.6469350457191467,
+      "learning_rate": 0.0002,
+      "loss": 0.3002,
+      "step": 5740
+    },
+    {
+      "epoch": 7.063882063882064,
+      "grad_norm": 0.8406739234924316,
+      "learning_rate": 0.0002,
+      "loss": 0.3046,
+      "step": 5750
+    },
+    {
+      "epoch": 7.076167076167076,
+      "grad_norm": 0.9954310059547424,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 5760
+    },
+    {
+      "epoch": 7.0884520884520885,
+      "grad_norm": 0.7063487768173218,
+      "learning_rate": 0.0002,
+      "loss": 0.3076,
+      "step": 5770
+    },
+    {
+      "epoch": 7.100737100737101,
+      "grad_norm": 0.8696660995483398,
+      "learning_rate": 0.0002,
+      "loss": 0.3033,
+      "step": 5780
+    },
+    {
+      "epoch": 7.113022113022113,
+      "grad_norm": 0.8088991045951843,
+      "learning_rate": 0.0002,
+      "loss": 0.3049,
+      "step": 5790
+    },
+    {
+      "epoch": 7.125307125307125,
+      "grad_norm": 0.6934662461280823,
+      "learning_rate": 0.0002,
+      "loss": 0.3042,
+      "step": 5800
+    },
+    {
+      "epoch": 7.137592137592137,
+      "grad_norm": 0.7482573390007019,
+      "learning_rate": 0.0002,
+      "loss": 0.3068,
+      "step": 5810
+    },
+    {
+      "epoch": 7.14987714987715,
+      "grad_norm": 1.0848287343978882,
+      "learning_rate": 0.0002,
+      "loss": 0.3001,
+      "step": 5820
+    },
+    {
+      "epoch": 7.162162162162162,
+      "grad_norm": 0.8017896413803101,
+      "learning_rate": 0.0002,
+      "loss": 0.3017,
+      "step": 5830
+    },
+    {
+      "epoch": 7.174447174447175,
+      "grad_norm": 0.6418949365615845,
+      "learning_rate": 0.0002,
+      "loss": 0.3051,
+      "step": 5840
+    },
+    {
+      "epoch": 7.186732186732186,
+      "grad_norm": 0.666072428226471,
+      "learning_rate": 0.0002,
+      "loss": 0.3032,
+      "step": 5850
+    },
+    {
+      "epoch": 7.199017199017199,
+      "grad_norm": 0.7549816370010376,
+      "learning_rate": 0.0002,
+      "loss": 0.3131,
+      "step": 5860
+    },
+    {
+      "epoch": 7.211302211302211,
+      "grad_norm": 0.8756735920906067,
+      "learning_rate": 0.0002,
+      "loss": 0.3088,
+      "step": 5870
+    },
+    {
+      "epoch": 7.223587223587224,
+      "grad_norm": 0.6790788769721985,
+      "learning_rate": 0.0002,
+      "loss": 0.3022,
+      "step": 5880
+    },
+    {
+      "epoch": 7.235872235872236,
+      "grad_norm": 0.8388362526893616,
+      "learning_rate": 0.0002,
+      "loss": 0.3011,
+      "step": 5890
+    },
+    {
+      "epoch": 7.2481572481572485,
+      "grad_norm": 0.8915345668792725,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 5900
+    },
+    {
+      "epoch": 7.26044226044226,
+      "grad_norm": 0.9234250783920288,
+      "learning_rate": 0.0002,
+      "loss": 0.3086,
+      "step": 5910
+    },
+    {
+      "epoch": 7.2727272727272725,
+      "grad_norm": 0.5452191233634949,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 5920
+    },
+    {
+      "epoch": 7.285012285012285,
+      "grad_norm": 0.6100478172302246,
+      "learning_rate": 0.0002,
+      "loss": 0.3054,
+      "step": 5930
+    },
+    {
+      "epoch": 7.297297297297297,
+      "grad_norm": 0.6258270740509033,
+      "learning_rate": 0.0002,
+      "loss": 0.3073,
+      "step": 5940
+    },
+    {
+      "epoch": 7.30958230958231,
+      "grad_norm": 0.8540555834770203,
+      "learning_rate": 0.0002,
+      "loss": 0.3179,
+      "step": 5950
+    },
+    {
+      "epoch": 7.321867321867322,
+      "grad_norm": 0.8662564754486084,
+      "learning_rate": 0.0002,
+      "loss": 0.3109,
+      "step": 5960
+    },
+    {
+      "epoch": 7.334152334152334,
+      "grad_norm": 0.7404284477233887,
+      "learning_rate": 0.0002,
+      "loss": 0.3039,
+      "step": 5970
+    },
+    {
+      "epoch": 7.346437346437346,
+      "grad_norm": 0.7579419612884521,
+      "learning_rate": 0.0002,
+      "loss": 0.3036,
+      "step": 5980
+    },
+    {
+      "epoch": 7.358722358722359,
+      "grad_norm": 0.7248510122299194,
+      "learning_rate": 0.0002,
+      "loss": 0.3113,
+      "step": 5990
+    },
+    {
+      "epoch": 7.371007371007371,
+      "grad_norm": 0.8882181644439697,
+      "learning_rate": 0.0002,
+      "loss": 0.2987,
+      "step": 6000
+    },
+    {
+      "epoch": 7.383292383292384,
+      "grad_norm": 0.8494889736175537,
+      "learning_rate": 0.0002,
+      "loss": 0.3026,
+      "step": 6010
+    },
+    {
+      "epoch": 7.395577395577396,
+      "grad_norm": 0.8501948118209839,
+      "learning_rate": 0.0002,
+      "loss": 0.3147,
+      "step": 6020
+    },
+    {
+      "epoch": 7.407862407862408,
+      "grad_norm": 0.7228043079376221,
+      "learning_rate": 0.0002,
+      "loss": 0.3122,
+      "step": 6030
+    },
+    {
+      "epoch": 7.42014742014742,
+      "grad_norm": 0.7471523284912109,
+      "learning_rate": 0.0002,
+      "loss": 0.3092,
+      "step": 6040
+    },
+    {
+      "epoch": 7.4324324324324325,
+      "grad_norm": 0.810962975025177,
+      "learning_rate": 0.0002,
+      "loss": 0.307,
+      "step": 6050
+    },
+    {
+      "epoch": 7.444717444717445,
+      "grad_norm": 1.0621764659881592,
+      "learning_rate": 0.0002,
+      "loss": 0.3024,
+      "step": 6060
+    },
+    {
+      "epoch": 7.457002457002457,
+      "grad_norm": 0.72637939453125,
+      "learning_rate": 0.0002,
+      "loss": 0.3019,
+      "step": 6070
+    },
+    {
+      "epoch": 7.469287469287469,
+      "grad_norm": 1.1550157070159912,
+      "learning_rate": 0.0002,
+      "loss": 0.314,
+      "step": 6080
+    },
+    {
+      "epoch": 7.481572481572481,
+      "grad_norm": 0.865250825881958,
+      "learning_rate": 0.0002,
+      "loss": 0.3088,
+      "step": 6090
+    },
+    {
+      "epoch": 7.493857493857494,
+      "grad_norm": 0.8407077789306641,
+      "learning_rate": 0.0002,
+      "loss": 0.3041,
+      "step": 6100
+    },
+    {
+      "epoch": 7.506142506142506,
+      "grad_norm": 0.7295752167701721,
+      "learning_rate": 0.0002,
+      "loss": 0.3064,
+      "step": 6110
+    },
+    {
+      "epoch": 7.518427518427519,
+      "grad_norm": 0.9728897213935852,
+      "learning_rate": 0.0002,
+      "loss": 0.3061,
+      "step": 6120
+    },
+    {
+      "epoch": 7.530712530712531,
+      "grad_norm": 0.9776952862739563,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 6130
+    },
+    {
+      "epoch": 7.542997542997543,
+      "grad_norm": 0.704113245010376,
+      "learning_rate": 0.0002,
+      "loss": 0.3148,
+      "step": 6140
+    },
+    {
+      "epoch": 7.555282555282555,
+      "grad_norm": 0.9030590057373047,
+      "learning_rate": 0.0002,
+      "loss": 0.3012,
+      "step": 6150
+    },
+    {
+      "epoch": 7.5675675675675675,
+      "grad_norm": 0.6629155874252319,
+      "learning_rate": 0.0002,
+      "loss": 0.3134,
+      "step": 6160
+    },
+    {
+      "epoch": 7.57985257985258,
+      "grad_norm": 0.9348171353340149,
+      "learning_rate": 0.0002,
+      "loss": 0.3068,
+      "step": 6170
+    },
+    {
+      "epoch": 7.592137592137592,
+      "grad_norm": 0.9363399744033813,
+      "learning_rate": 0.0002,
+      "loss": 0.3065,
+      "step": 6180
+    },
+    {
+      "epoch": 7.604422604422604,
+      "grad_norm": 0.902718186378479,
+      "learning_rate": 0.0002,
+      "loss": 0.3099,
+      "step": 6190
+    },
+    {
+      "epoch": 7.616707616707616,
+      "grad_norm": 0.6992074251174927,
+      "learning_rate": 0.0002,
+      "loss": 0.3082,
+      "step": 6200
+    },
+    {
+      "epoch": 7.628992628992629,
+      "grad_norm": 0.7574757933616638,
+      "learning_rate": 0.0002,
+      "loss": 0.2941,
+      "step": 6210
+    },
+    {
+      "epoch": 7.641277641277641,
+      "grad_norm": 0.7717660069465637,
+      "learning_rate": 0.0002,
+      "loss": 0.3079,
+      "step": 6220
+    },
+    {
+      "epoch": 7.653562653562654,
+      "grad_norm": 0.7789981961250305,
+      "learning_rate": 0.0002,
+      "loss": 0.3005,
+      "step": 6230
+    },
+    {
+      "epoch": 7.665847665847666,
+      "grad_norm": 1.1020026206970215,
+      "learning_rate": 0.0002,
+      "loss": 0.3112,
+      "step": 6240
+    },
+    {
+      "epoch": 7.678132678132678,
+      "grad_norm": 0.7290350794792175,
+      "learning_rate": 0.0002,
+      "loss": 0.3087,
+      "step": 6250
+    },
+    {
+      "epoch": 7.69041769041769,
+      "grad_norm": 0.7291128039360046,
+      "learning_rate": 0.0002,
+      "loss": 0.3023,
+      "step": 6260
+    },
+    {
+      "epoch": 7.702702702702703,
+      "grad_norm": 0.7766857147216797,
+      "learning_rate": 0.0002,
+      "loss": 0.3019,
+      "step": 6270
+    },
+    {
+      "epoch": 7.714987714987715,
+      "grad_norm": 0.938277542591095,
+      "learning_rate": 0.0002,
+      "loss": 0.3039,
+      "step": 6280
+    },
+    {
+      "epoch": 7.7272727272727275,
+      "grad_norm": 0.785190761089325,
+      "learning_rate": 0.0002,
+      "loss": 0.3103,
+      "step": 6290
+    },
+    {
+      "epoch": 7.739557739557739,
+      "grad_norm": 0.7140066623687744,
+      "learning_rate": 0.0002,
+      "loss": 0.2938,
+      "step": 6300
+    },
+    {
+      "epoch": 7.7518427518427515,
+      "grad_norm": 0.9476789236068726,
+      "learning_rate": 0.0002,
+      "loss": 0.3042,
+      "step": 6310
+    },
+    {
+      "epoch": 7.764127764127764,
+      "grad_norm": 0.6404930949211121,
+      "learning_rate": 0.0002,
+      "loss": 0.3035,
+      "step": 6320
+    },
+    {
+      "epoch": 7.776412776412776,
+      "grad_norm": 0.6433947682380676,
+      "learning_rate": 0.0002,
+      "loss": 0.3065,
+      "step": 6330
+    },
+    {
+      "epoch": 7.788697788697789,
+      "grad_norm": 0.8289583921432495,
+      "learning_rate": 0.0002,
+      "loss": 0.3117,
+      "step": 6340
+    },
+    {
+      "epoch": 7.800982800982801,
+      "grad_norm": 1.098555088043213,
+      "learning_rate": 0.0002,
+      "loss": 0.3057,
+      "step": 6350
+    },
+    {
+      "epoch": 7.813267813267814,
+      "grad_norm": 0.7225303053855896,
+      "learning_rate": 0.0002,
+      "loss": 0.3104,
+      "step": 6360
+    },
+    {
+      "epoch": 7.825552825552825,
+      "grad_norm": 0.845711886882782,
+      "learning_rate": 0.0002,
+      "loss": 0.3043,
+      "step": 6370
+    },
+    {
+      "epoch": 7.837837837837838,
+      "grad_norm": 0.6199421882629395,
+      "learning_rate": 0.0002,
+      "loss": 0.3099,
+      "step": 6380
+    },
+    {
+      "epoch": 7.85012285012285,
+      "grad_norm": 0.7576995491981506,
+      "learning_rate": 0.0002,
+      "loss": 0.3095,
+      "step": 6390
+    },
+    {
+      "epoch": 7.862407862407863,
+      "grad_norm": 0.6669192314147949,
+      "learning_rate": 0.0002,
+      "loss": 0.311,
+      "step": 6400
+    },
+    {
+      "epoch": 7.874692874692875,
+      "grad_norm": 0.6896083354949951,
+      "learning_rate": 0.0002,
+      "loss": 0.2953,
+      "step": 6410
+    },
+    {
+      "epoch": 7.886977886977887,
+      "grad_norm": 0.9418429732322693,
+      "learning_rate": 0.0002,
+      "loss": 0.3,
+      "step": 6420
+    },
+    {
+      "epoch": 7.899262899262899,
+      "grad_norm": 0.7120184302330017,
+      "learning_rate": 0.0002,
+      "loss": 0.3074,
+      "step": 6430
+    },
+    {
+      "epoch": 7.9115479115479115,
+      "grad_norm": 0.7420004606246948,
+      "learning_rate": 0.0002,
+      "loss": 0.3158,
+      "step": 6440
+    },
+    {
+      "epoch": 7.923832923832924,
+      "grad_norm": 0.8989502191543579,
+      "learning_rate": 0.0002,
+      "loss": 0.3068,
+      "step": 6450
+    },
+    {
+      "epoch": 7.936117936117936,
+      "grad_norm": 0.715905487537384,
+      "learning_rate": 0.0002,
+      "loss": 0.3102,
+      "step": 6460
+    },
+    {
+      "epoch": 7.948402948402949,
+      "grad_norm": 0.8890138268470764,
+      "learning_rate": 0.0002,
+      "loss": 0.3018,
+      "step": 6470
+    },
+    {
+      "epoch": 7.96068796068796,
+      "grad_norm": 0.7992095351219177,
+      "learning_rate": 0.0002,
+      "loss": 0.3179,
+      "step": 6480
+    },
+    {
+      "epoch": 7.972972972972973,
+      "grad_norm": 0.9169677495956421,
+      "learning_rate": 0.0002,
+      "loss": 0.3115,
+      "step": 6490
+    },
+    {
+      "epoch": 7.985257985257985,
+      "grad_norm": 0.7911704778671265,
+      "learning_rate": 0.0002,
+      "loss": 0.3001,
+      "step": 6500
+    },
+    {
+      "epoch": 7.997542997542998,
+      "grad_norm": 0.8787347078323364,
+      "learning_rate": 0.0002,
+      "loss": 0.3085,
+      "step": 6510
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.3476468026638031,
+      "eval_runtime": 20.9232,
+      "eval_samples_per_second": 15.82,
+      "eval_steps_per_second": 2.007,
+      "step": 6512
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 7.958964013419725e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-6512/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/README.md b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..830a14f7db2734beb59f320973504e45a3fe87f5
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/adapter_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..600a5ae79fa5bbcdea8bd42ae99abf77134a3287
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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": [
+    "v_proj",
+    "q_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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/adapter_model.safetensors b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0557e6278d7e5434c1724923fd94e6ab372c2eb6
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b932857e7e169f54985be4155c82c5991b9ccf04f8b215a8cf1e7606fbe01d22
+size 29500848
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/optimizer.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b9a5cbe56431906db3166b1329c624c9ab93850f
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75284599f62765ab7b0ddae65d53b349bdbc499903f800fbec384703f3e0a79
+size 15064314
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/rng_state.pth b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7a291025dbb6b5c8f81d0bb7959bdee7783241af
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba23d88dd13bbc4ba62dd650687135927fc2f9b25562c44aeaad88e5492194f
+size 14244
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/scheduler.pt b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d81af9d9349962f0edb5857b472dcfaebe70d51f
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eed6d80e68918f4258337b1cdd6e535070c3495c8e1af817b56814ff10e2a2a
+size 1064
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/trainer_state.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..179da97e82ab42b6e59524481c9107242d96ae7c
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/trainer_state.json
@@ -0,0 +1,608 @@
+{
+  "best_metric": 0.703994870185852,
+  "best_model_checkpoint": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814",
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012285012285012284,
+      "grad_norm": 0.8178550004959106,
+      "learning_rate": 0.0002,
+      "loss": 3.5354,
+      "step": 10
+    },
+    {
+      "epoch": 0.02457002457002457,
+      "grad_norm": 1.0338047742843628,
+      "learning_rate": 0.0002,
+      "loss": 2.534,
+      "step": 20
+    },
+    {
+      "epoch": 0.036855036855036855,
+      "grad_norm": 0.8931729197502136,
+      "learning_rate": 0.0002,
+      "loss": 2.1691,
+      "step": 30
+    },
+    {
+      "epoch": 0.04914004914004914,
+      "grad_norm": 0.9666458964347839,
+      "learning_rate": 0.0002,
+      "loss": 1.8813,
+      "step": 40
+    },
+    {
+      "epoch": 0.06142506142506143,
+      "grad_norm": 1.2691702842712402,
+      "learning_rate": 0.0002,
+      "loss": 1.6479,
+      "step": 50
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 1.0307111740112305,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 60
+    },
+    {
+      "epoch": 0.085995085995086,
+      "grad_norm": 1.1837389469146729,
+      "learning_rate": 0.0002,
+      "loss": 1.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.09828009828009827,
+      "grad_norm": 1.1481467485427856,
+      "learning_rate": 0.0002,
+      "loss": 1.2325,
+      "step": 80
+    },
+    {
+      "epoch": 0.11056511056511056,
+      "grad_norm": 1.0385297536849976,
+      "learning_rate": 0.0002,
+      "loss": 1.1425,
+      "step": 90
+    },
+    {
+      "epoch": 0.12285012285012285,
+      "grad_norm": 1.125789999961853,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 100
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.9630613923072815,
+      "learning_rate": 0.0002,
+      "loss": 1.0477,
+      "step": 110
+    },
+    {
+      "epoch": 0.14742014742014742,
+      "grad_norm": 1.060392141342163,
+      "learning_rate": 0.0002,
+      "loss": 1.0074,
+      "step": 120
+    },
+    {
+      "epoch": 0.1597051597051597,
+      "grad_norm": 1.0986546277999878,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 130
+    },
+    {
+      "epoch": 0.171990171990172,
+      "grad_norm": 1.1713459491729736,
+      "learning_rate": 0.0002,
+      "loss": 1.0068,
+      "step": 140
+    },
+    {
+      "epoch": 0.18427518427518427,
+      "grad_norm": 1.1548224687576294,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "step": 150
+    },
+    {
+      "epoch": 0.19656019656019655,
+      "grad_norm": 1.2662502527236938,
+      "learning_rate": 0.0002,
+      "loss": 0.941,
+      "step": 160
+    },
+    {
+      "epoch": 0.20884520884520885,
+      "grad_norm": 1.1521110534667969,
+      "learning_rate": 0.0002,
+      "loss": 0.8849,
+      "step": 170
+    },
+    {
+      "epoch": 0.22113022113022113,
+      "grad_norm": 1.1044857501983643,
+      "learning_rate": 0.0002,
+      "loss": 0.8931,
+      "step": 180
+    },
+    {
+      "epoch": 0.2334152334152334,
+      "grad_norm": 0.9770650267601013,
+      "learning_rate": 0.0002,
+      "loss": 0.9572,
+      "step": 190
+    },
+    {
+      "epoch": 0.2457002457002457,
+      "grad_norm": 0.9710931777954102,
+      "learning_rate": 0.0002,
+      "loss": 0.881,
+      "step": 200
+    },
+    {
+      "epoch": 0.257985257985258,
+      "grad_norm": 0.9593933820724487,
+      "learning_rate": 0.0002,
+      "loss": 0.9205,
+      "step": 210
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 1.003553032875061,
+      "learning_rate": 0.0002,
+      "loss": 0.843,
+      "step": 220
+    },
+    {
+      "epoch": 0.28255528255528256,
+      "grad_norm": 0.9187764525413513,
+      "learning_rate": 0.0002,
+      "loss": 0.9032,
+      "step": 230
+    },
+    {
+      "epoch": 0.29484029484029484,
+      "grad_norm": 0.9294946789741516,
+      "learning_rate": 0.0002,
+      "loss": 0.8572,
+      "step": 240
+    },
+    {
+      "epoch": 0.3071253071253071,
+      "grad_norm": 0.9537560939788818,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 0.3194103194103194,
+      "grad_norm": 1.00537109375,
+      "learning_rate": 0.0002,
+      "loss": 0.8546,
+      "step": 260
+    },
+    {
+      "epoch": 0.3316953316953317,
+      "grad_norm": 0.8775776028633118,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 270
+    },
+    {
+      "epoch": 0.343980343980344,
+      "grad_norm": 0.8316839933395386,
+      "learning_rate": 0.0002,
+      "loss": 0.808,
+      "step": 280
+    },
+    {
+      "epoch": 0.35626535626535627,
+      "grad_norm": 0.8542073965072632,
+      "learning_rate": 0.0002,
+      "loss": 0.8248,
+      "step": 290
+    },
+    {
+      "epoch": 0.36855036855036855,
+      "grad_norm": 0.848444402217865,
+      "learning_rate": 0.0002,
+      "loss": 0.8452,
+      "step": 300
+    },
+    {
+      "epoch": 0.3808353808353808,
+      "grad_norm": 0.9017520546913147,
+      "learning_rate": 0.0002,
+      "loss": 0.8253,
+      "step": 310
+    },
+    {
+      "epoch": 0.3931203931203931,
+      "grad_norm": 0.7672467231750488,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 320
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.9109916687011719,
+      "learning_rate": 0.0002,
+      "loss": 0.8478,
+      "step": 330
+    },
+    {
+      "epoch": 0.4176904176904177,
+      "grad_norm": 0.8750321269035339,
+      "learning_rate": 0.0002,
+      "loss": 0.8041,
+      "step": 340
+    },
+    {
+      "epoch": 0.42997542997543,
+      "grad_norm": 0.7911098599433899,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 350
+    },
+    {
+      "epoch": 0.44226044226044225,
+      "grad_norm": 0.871601402759552,
+      "learning_rate": 0.0002,
+      "loss": 0.8001,
+      "step": 360
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.9393917918205261,
+      "learning_rate": 0.0002,
+      "loss": 0.8187,
+      "step": 370
+    },
+    {
+      "epoch": 0.4668304668304668,
+      "grad_norm": 0.8260403275489807,
+      "learning_rate": 0.0002,
+      "loss": 0.8124,
+      "step": 380
+    },
+    {
+      "epoch": 0.47911547911547914,
+      "grad_norm": 0.9792159199714661,
+      "learning_rate": 0.0002,
+      "loss": 0.7768,
+      "step": 390
+    },
+    {
+      "epoch": 0.4914004914004914,
+      "grad_norm": 0.9943315982818604,
+      "learning_rate": 0.0002,
+      "loss": 0.7981,
+      "step": 400
+    },
+    {
+      "epoch": 0.5036855036855037,
+      "grad_norm": 0.8999950885772705,
+      "learning_rate": 0.0002,
+      "loss": 0.7765,
+      "step": 410
+    },
+    {
+      "epoch": 0.515970515970516,
+      "grad_norm": 0.8348393440246582,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 420
+    },
+    {
+      "epoch": 0.5282555282555282,
+      "grad_norm": 0.7371744513511658,
+      "learning_rate": 0.0002,
+      "loss": 0.8269,
+      "step": 430
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8354107141494751,
+      "learning_rate": 0.0002,
+      "loss": 0.8181,
+      "step": 440
+    },
+    {
+      "epoch": 0.5528255528255528,
+      "grad_norm": 0.8553793430328369,
+      "learning_rate": 0.0002,
+      "loss": 0.7849,
+      "step": 450
+    },
+    {
+      "epoch": 0.5651105651105651,
+      "grad_norm": 1.0762015581130981,
+      "learning_rate": 0.0002,
+      "loss": 0.8098,
+      "step": 460
+    },
+    {
+      "epoch": 0.5773955773955773,
+      "grad_norm": 0.8350747227668762,
+      "learning_rate": 0.0002,
+      "loss": 0.7942,
+      "step": 470
+    },
+    {
+      "epoch": 0.5896805896805897,
+      "grad_norm": 0.7819945216178894,
+      "learning_rate": 0.0002,
+      "loss": 0.7922,
+      "step": 480
+    },
+    {
+      "epoch": 0.601965601965602,
+      "grad_norm": 0.8079741597175598,
+      "learning_rate": 0.0002,
+      "loss": 0.7845,
+      "step": 490
+    },
+    {
+      "epoch": 0.6142506142506142,
+      "grad_norm": 0.776435911655426,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 500
+    },
+    {
+      "epoch": 0.6265356265356266,
+      "grad_norm": 0.7646855115890503,
+      "learning_rate": 0.0002,
+      "loss": 0.7855,
+      "step": 510
+    },
+    {
+      "epoch": 0.6388206388206388,
+      "grad_norm": 0.786396861076355,
+      "learning_rate": 0.0002,
+      "loss": 0.7923,
+      "step": 520
+    },
+    {
+      "epoch": 0.6511056511056511,
+      "grad_norm": 0.7016594409942627,
+      "learning_rate": 0.0002,
+      "loss": 0.7624,
+      "step": 530
+    },
+    {
+      "epoch": 0.6633906633906634,
+      "grad_norm": 0.8060444593429565,
+      "learning_rate": 0.0002,
+      "loss": 0.786,
+      "step": 540
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.9087467789649963,
+      "learning_rate": 0.0002,
+      "loss": 0.7417,
+      "step": 550
+    },
+    {
+      "epoch": 0.687960687960688,
+      "grad_norm": 0.8149628639221191,
+      "learning_rate": 0.0002,
+      "loss": 0.7591,
+      "step": 560
+    },
+    {
+      "epoch": 0.7002457002457002,
+      "grad_norm": 0.7493641972541809,
+      "learning_rate": 0.0002,
+      "loss": 0.8004,
+      "step": 570
+    },
+    {
+      "epoch": 0.7125307125307125,
+      "grad_norm": 0.7958765625953674,
+      "learning_rate": 0.0002,
+      "loss": 0.765,
+      "step": 580
+    },
+    {
+      "epoch": 0.7248157248157249,
+      "grad_norm": 0.7917273640632629,
+      "learning_rate": 0.0002,
+      "loss": 0.7276,
+      "step": 590
+    },
+    {
+      "epoch": 0.7371007371007371,
+      "grad_norm": 0.8040468692779541,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 600
+    },
+    {
+      "epoch": 0.7493857493857494,
+      "grad_norm": 0.8696851134300232,
+      "learning_rate": 0.0002,
+      "loss": 0.735,
+      "step": 610
+    },
+    {
+      "epoch": 0.7616707616707616,
+      "grad_norm": 0.8418059945106506,
+      "learning_rate": 0.0002,
+      "loss": 0.7321,
+      "step": 620
+    },
+    {
+      "epoch": 0.773955773955774,
+      "grad_norm": 0.7754243612289429,
+      "learning_rate": 0.0002,
+      "loss": 0.7395,
+      "step": 630
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.7639613747596741,
+      "learning_rate": 0.0002,
+      "loss": 0.7679,
+      "step": 640
+    },
+    {
+      "epoch": 0.7985257985257985,
+      "grad_norm": 0.7516646385192871,
+      "learning_rate": 0.0002,
+      "loss": 0.7159,
+      "step": 650
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.7840844988822937,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 660
+    },
+    {
+      "epoch": 0.8230958230958231,
+      "grad_norm": 0.7657070755958557,
+      "learning_rate": 0.0002,
+      "loss": 0.7264,
+      "step": 670
+    },
+    {
+      "epoch": 0.8353808353808354,
+      "grad_norm": 0.7711591720581055,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 680
+    },
+    {
+      "epoch": 0.8476658476658476,
+      "grad_norm": 0.8026325106620789,
+      "learning_rate": 0.0002,
+      "loss": 0.759,
+      "step": 690
+    },
+    {
+      "epoch": 0.85995085995086,
+      "grad_norm": 0.7902713418006897,
+      "learning_rate": 0.0002,
+      "loss": 0.737,
+      "step": 700
+    },
+    {
+      "epoch": 0.8722358722358723,
+      "grad_norm": 0.8212456107139587,
+      "learning_rate": 0.0002,
+      "loss": 0.7349,
+      "step": 710
+    },
+    {
+      "epoch": 0.8845208845208845,
+      "grad_norm": 0.7867200970649719,
+      "learning_rate": 0.0002,
+      "loss": 0.7661,
+      "step": 720
+    },
+    {
+      "epoch": 0.8968058968058968,
+      "grad_norm": 0.80084627866745,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 730
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.7203794121742249,
+      "learning_rate": 0.0002,
+      "loss": 0.7641,
+      "step": 740
+    },
+    {
+      "epoch": 0.9213759213759214,
+      "grad_norm": 0.7598419785499573,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 750
+    },
+    {
+      "epoch": 0.9336609336609336,
+      "grad_norm": 0.7787027359008789,
+      "learning_rate": 0.0002,
+      "loss": 0.7208,
+      "step": 760
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.8444012403488159,
+      "learning_rate": 0.0002,
+      "loss": 0.7119,
+      "step": 770
+    },
+    {
+      "epoch": 0.9582309582309583,
+      "grad_norm": 0.7388550639152527,
+      "learning_rate": 0.0002,
+      "loss": 0.7099,
+      "step": 780
+    },
+    {
+      "epoch": 0.9705159705159705,
+      "grad_norm": 0.7379167079925537,
+      "learning_rate": 0.0002,
+      "loss": 0.7184,
+      "step": 790
+    },
+    {
+      "epoch": 0.9828009828009828,
+      "grad_norm": 0.8291640281677246,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 800
+    },
+    {
+      "epoch": 0.995085995085995,
+      "grad_norm": 0.7415094375610352,
+      "learning_rate": 0.0002,
+      "loss": 0.6972,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703994870185852,
+      "eval_runtime": 20.2182,
+      "eval_samples_per_second": 16.371,
+      "eval_steps_per_second": 2.077,
+      "step": 814
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6512,
+  "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": 9948705016774656.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/special_tokens_map.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..f58963a682665634ab180c28667e4faa8cf02ba2
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer.model b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer_config.json b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1adb4796c13b8d975555ecec45876ee75d1ae8b7
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/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-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_args.bin b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73a75ebfc12aed51385aab437d91632ee4c20317
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2809e8544b7de8b298d0b325fb6c98eb9f853fd72d7cbae286b6ee1541e6aee9
+size 5560
diff --git a/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_log.jsonl b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..60b058e92ac7e4c2cd4dc10d82be965dee8bfda6
--- /dev/null
+++ b/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/training_log.jsonl
@@ -0,0 +1,8 @@
+{"epoch": 1.0, "step": 814, "epoch_duration": 749.2984616756439, "total_accumulated_duration": 749.2984616756439, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}]}
+{"epoch": 2.0, "step": 1628, "epoch_duration": 737.6845755577087, "total_accumulated_duration": 1486.9830372333527, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-814", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}]}
+{"epoch": 3.0, "step": 2442, "epoch_duration": 735.7253043651581, "total_accumulated_duration": 2222.7083415985107, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-1628", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}]}
+{"epoch": 4.0, "step": 3256, "epoch_duration": 710.208240032196, "total_accumulated_duration": 2932.916581630707, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-2442", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}, {"eval_loss": 0.49752503633499146, "eval_runtime": 20.2911, "eval_samples_per_second": 16.313, "eval_steps_per_second": 2.07, "epoch": 3.0, "step": 2442}, {"loss": 0.4362, "grad_norm": 0.7644656896591187, "learning_rate": 0.0002, "epoch": 3.0098280098280097, "step": 2450}, {"loss": 0.4363, "grad_norm": 0.9077525734901428, "learning_rate": 0.0002, "epoch": 3.022113022113022, "step": 2460}, {"loss": 0.422, "grad_norm": 0.7859287261962891, "learning_rate": 0.0002, "epoch": 3.0343980343980346, "step": 2470}, {"loss": 0.4574, "grad_norm": 1.1200323104858398, "learning_rate": 0.0002, "epoch": 3.0466830466830466, "step": 2480}, {"loss": 0.4519, "grad_norm": 0.7570453882217407, "learning_rate": 0.0002, "epoch": 3.058968058968059, "step": 2490}, {"loss": 0.4351, "grad_norm": 0.9450915455818176, "learning_rate": 0.0002, "epoch": 3.0712530712530715, "step": 2500}, {"loss": 0.4343, "grad_norm": 0.8303545117378235, "learning_rate": 0.0002, "epoch": 3.0835380835380835, "step": 2510}, {"loss": 0.4308, "grad_norm": 0.8864443898200989, "learning_rate": 0.0002, "epoch": 3.095823095823096, "step": 2520}, {"loss": 0.4601, "grad_norm": 0.945324718952179, "learning_rate": 0.0002, "epoch": 3.108108108108108, "step": 2530}, {"loss": 0.4345, "grad_norm": 1.0562494993209839, "learning_rate": 0.0002, "epoch": 3.1203931203931203, "step": 2540}, {"loss": 0.4375, "grad_norm": 0.8607500195503235, "learning_rate": 0.0002, "epoch": 3.1326781326781328, "step": 2550}, {"loss": 0.456, "grad_norm": 0.8719640374183655, "learning_rate": 0.0002, "epoch": 3.1449631449631448, "step": 2560}, {"loss": 0.4469, "grad_norm": 0.8647059202194214, "learning_rate": 0.0002, "epoch": 3.157248157248157, "step": 2570}, {"loss": 0.4483, "grad_norm": 0.8346507549285889, "learning_rate": 0.0002, "epoch": 3.1695331695331697, "step": 2580}, {"loss": 0.4331, "grad_norm": 1.0208854675292969, "learning_rate": 0.0002, "epoch": 3.1818181818181817, "step": 2590}, {"loss": 0.435, "grad_norm": 0.7064385414123535, "learning_rate": 0.0002, "epoch": 3.194103194103194, "step": 2600}, {"loss": 0.4541, "grad_norm": 0.927347719669342, "learning_rate": 0.0002, "epoch": 3.2063882063882065, "step": 2610}, {"loss": 0.4561, "grad_norm": 0.943517804145813, "learning_rate": 0.0002, "epoch": 3.2186732186732185, "step": 2620}, {"loss": 0.4225, "grad_norm": 0.7837198376655579, "learning_rate": 0.0002, "epoch": 3.230958230958231, "step": 2630}, {"loss": 0.4494, "grad_norm": 0.7752765417098999, "learning_rate": 0.0002, "epoch": 3.2432432432432434, "step": 2640}, {"loss": 0.4468, "grad_norm": 0.8578953146934509, "learning_rate": 0.0002, "epoch": 3.2555282555282554, "step": 2650}, {"loss": 0.4393, "grad_norm": 1.0209529399871826, "learning_rate": 0.0002, "epoch": 3.267813267813268, "step": 2660}, {"loss": 0.4517, "grad_norm": 0.9069030284881592, "learning_rate": 0.0002, "epoch": 3.2800982800982803, "step": 2670}, {"loss": 0.4262, "grad_norm": 0.8454729318618774, "learning_rate": 0.0002, "epoch": 3.2923832923832923, "step": 2680}, {"loss": 0.4349, "grad_norm": 0.8253099322319031, "learning_rate": 0.0002, "epoch": 3.3046683046683047, "step": 2690}, {"loss": 0.4503, "grad_norm": 0.8765934109687805, "learning_rate": 0.0002, "epoch": 3.3169533169533167, "step": 2700}, {"loss": 0.4518, "grad_norm": 0.8149126172065735, "learning_rate": 0.0002, "epoch": 3.329238329238329, "step": 2710}, {"loss": 0.4437, "grad_norm": 0.8820102214813232, "learning_rate": 0.0002, "epoch": 3.3415233415233416, "step": 2720}, {"loss": 0.4346, "grad_norm": 0.8813952803611755, "learning_rate": 0.0002, "epoch": 3.3538083538083536, "step": 2730}, {"loss": 0.4396, "grad_norm": 1.0338447093963623, "learning_rate": 0.0002, "epoch": 3.366093366093366, "step": 2740}, {"loss": 0.4468, "grad_norm": 0.8780209422111511, "learning_rate": 0.0002, "epoch": 3.3783783783783785, "step": 2750}, {"loss": 0.441, "grad_norm": 0.9017151594161987, "learning_rate": 0.0002, "epoch": 3.3906633906633905, "step": 2760}, {"loss": 0.446, "grad_norm": 0.8647638559341431, "learning_rate": 0.0002, "epoch": 3.402948402948403, "step": 2770}, {"loss": 0.4131, "grad_norm": 0.8298183679580688, "learning_rate": 0.0002, "epoch": 3.4152334152334154, "step": 2780}, {"loss": 0.4406, "grad_norm": 0.9298108816146851, "learning_rate": 0.0002, "epoch": 3.4275184275184274, "step": 2790}, {"loss": 0.4145, "grad_norm": 0.8909980058670044, "learning_rate": 0.0002, "epoch": 3.43980343980344, "step": 2800}, {"loss": 0.4148, "grad_norm": 0.8027496933937073, "learning_rate": 0.0002, "epoch": 3.4520884520884523, "step": 2810}, {"loss": 0.4244, "grad_norm": 0.8766195774078369, "learning_rate": 0.0002, "epoch": 3.4643734643734643, "step": 2820}, {"loss": 0.4292, "grad_norm": 0.8194443583488464, "learning_rate": 0.0002, "epoch": 3.4766584766584767, "step": 2830}, {"loss": 0.4305, "grad_norm": 0.9862873554229736, "learning_rate": 0.0002, "epoch": 3.488943488943489, "step": 2840}, {"loss": 0.4393, "grad_norm": 0.8755377531051636, "learning_rate": 0.0002, "epoch": 3.501228501228501, "step": 2850}, {"loss": 0.4231, "grad_norm": 0.7300266027450562, "learning_rate": 0.0002, "epoch": 3.5135135135135136, "step": 2860}, {"loss": 0.4278, "grad_norm": 0.8342461585998535, "learning_rate": 0.0002, "epoch": 3.5257985257985256, "step": 2870}, {"loss": 0.4395, "grad_norm": 0.8624151349067688, "learning_rate": 0.0002, "epoch": 3.538083538083538, "step": 2880}, {"loss": 0.4064, "grad_norm": 0.8931261301040649, "learning_rate": 0.0002, "epoch": 3.5503685503685505, "step": 2890}, {"loss": 0.4358, "grad_norm": 0.8617086410522461, "learning_rate": 0.0002, "epoch": 3.562653562653563, "step": 2900}, {"loss": 0.419, "grad_norm": 0.8754099607467651, "learning_rate": 0.0002, "epoch": 3.574938574938575, "step": 2910}, {"loss": 0.4275, "grad_norm": 0.8345834612846375, "learning_rate": 0.0002, "epoch": 3.5872235872235874, "step": 2920}, {"loss": 0.4375, "grad_norm": 1.1414062976837158, "learning_rate": 0.0002, "epoch": 3.5995085995085994, "step": 2930}, {"loss": 0.4297, "grad_norm": 0.994860053062439, "learning_rate": 0.0002, "epoch": 3.611793611793612, "step": 2940}, {"loss": 0.4386, "grad_norm": 1.19268000125885, "learning_rate": 0.0002, "epoch": 3.6240786240786242, "step": 2950}, {"loss": 0.4029, "grad_norm": 0.8399543762207031, "learning_rate": 0.0002, "epoch": 3.6363636363636362, "step": 2960}, {"loss": 0.4432, "grad_norm": 0.9873217940330505, "learning_rate": 0.0002, "epoch": 3.6486486486486487, "step": 2970}, {"loss": 0.4308, "grad_norm": 0.9116013646125793, "learning_rate": 0.0002, "epoch": 3.6609336609336607, "step": 2980}, {"loss": 0.4275, "grad_norm": 0.9503833651542664, "learning_rate": 0.0002, "epoch": 3.673218673218673, "step": 2990}, {"loss": 0.4306, "grad_norm": 0.9401112794876099, "learning_rate": 0.0002, "epoch": 3.6855036855036856, "step": 3000}, {"loss": 0.4333, "grad_norm": 1.00745689868927, "learning_rate": 0.0002, "epoch": 3.697788697788698, "step": 3010}, {"loss": 0.432, "grad_norm": 1.0553191900253296, "learning_rate": 0.0002, "epoch": 3.71007371007371, "step": 3020}, {"loss": 0.4321, "grad_norm": 1.0226953029632568, "learning_rate": 0.0002, "epoch": 3.7223587223587224, "step": 3030}, {"loss": 0.418, "grad_norm": 1.085554838180542, "learning_rate": 0.0002, "epoch": 3.7346437346437344, "step": 3040}, {"loss": 0.4196, "grad_norm": 0.9948731064796448, "learning_rate": 0.0002, "epoch": 3.746928746928747, "step": 3050}, {"loss": 0.4281, "grad_norm": 0.9328727126121521, "learning_rate": 0.0002, "epoch": 3.7592137592137593, "step": 3060}, {"loss": 0.4284, "grad_norm": 1.0533266067504883, "learning_rate": 0.0002, "epoch": 3.7714987714987718, "step": 3070}, {"loss": 0.4414, "grad_norm": 0.8213809132575989, "learning_rate": 0.0002, "epoch": 3.7837837837837838, "step": 3080}, {"loss": 0.4348, "grad_norm": 0.8941594362258911, "learning_rate": 0.0002, "epoch": 3.796068796068796, "step": 3090}, {"loss": 0.4266, "grad_norm": 0.8324518203735352, "learning_rate": 0.0002, "epoch": 3.808353808353808, "step": 3100}, {"loss": 0.4227, "grad_norm": 0.8811233639717102, "learning_rate": 0.0002, "epoch": 3.8206388206388207, "step": 3110}, {"loss": 0.4195, "grad_norm": 0.8781470060348511, "learning_rate": 0.0002, "epoch": 3.832923832923833, "step": 3120}, {"loss": 0.4277, "grad_norm": 0.8994116187095642, "learning_rate": 0.0002, "epoch": 3.845208845208845, "step": 3130}, {"loss": 0.4149, "grad_norm": 0.8605017066001892, "learning_rate": 0.0002, "epoch": 3.8574938574938575, "step": 3140}, {"loss": 0.4023, "grad_norm": 0.8966400027275085, "learning_rate": 0.0002, "epoch": 3.8697788697788695, "step": 3150}, {"loss": 0.4245, "grad_norm": 0.8856554627418518, "learning_rate": 0.0002, "epoch": 3.882063882063882, "step": 3160}, {"loss": 0.4101, "grad_norm": 0.8971620798110962, "learning_rate": 0.0002, "epoch": 3.8943488943488944, "step": 3170}, {"loss": 0.3993, "grad_norm": 0.9807813167572021, "learning_rate": 0.0002, "epoch": 3.906633906633907, "step": 3180}, {"loss": 0.4258, "grad_norm": 0.8614121675491333, "learning_rate": 0.0002, "epoch": 3.918918918918919, "step": 3190}, {"loss": 0.4115, "grad_norm": 0.989171028137207, "learning_rate": 0.0002, "epoch": 3.9312039312039313, "step": 3200}, {"loss": 0.4182, "grad_norm": 0.8168872594833374, "learning_rate": 0.0002, "epoch": 3.9434889434889433, "step": 3210}, {"loss": 0.4112, "grad_norm": 0.8109386563301086, "learning_rate": 0.0002, "epoch": 3.9557739557739557, "step": 3220}, {"loss": 0.4165, "grad_norm": 1.0175853967666626, "learning_rate": 0.0002, "epoch": 3.968058968058968, "step": 3230}, {"loss": 0.4146, "grad_norm": 0.936143159866333, "learning_rate": 0.0002, "epoch": 3.98034398034398, "step": 3240}, {"loss": 0.4163, "grad_norm": 0.9557915925979614, "learning_rate": 0.0002, "epoch": 3.9926289926289926, "step": 3250}]}
+{"epoch": 5.0, "step": 4070, "epoch_duration": 777.9073820114136, "total_accumulated_duration": 3710.8239636421204, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-3256", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}, {"eval_loss": 0.49752503633499146, "eval_runtime": 20.2911, "eval_samples_per_second": 16.313, "eval_steps_per_second": 2.07, "epoch": 3.0, "step": 2442}, {"loss": 0.4362, "grad_norm": 0.7644656896591187, "learning_rate": 0.0002, "epoch": 3.0098280098280097, "step": 2450}, {"loss": 0.4363, "grad_norm": 0.9077525734901428, "learning_rate": 0.0002, "epoch": 3.022113022113022, "step": 2460}, {"loss": 0.422, "grad_norm": 0.7859287261962891, "learning_rate": 0.0002, "epoch": 3.0343980343980346, "step": 2470}, {"loss": 0.4574, "grad_norm": 1.1200323104858398, "learning_rate": 0.0002, "epoch": 3.0466830466830466, "step": 2480}, {"loss": 0.4519, "grad_norm": 0.7570453882217407, "learning_rate": 0.0002, "epoch": 3.058968058968059, "step": 2490}, {"loss": 0.4351, "grad_norm": 0.9450915455818176, "learning_rate": 0.0002, "epoch": 3.0712530712530715, "step": 2500}, {"loss": 0.4343, "grad_norm": 0.8303545117378235, "learning_rate": 0.0002, "epoch": 3.0835380835380835, "step": 2510}, {"loss": 0.4308, "grad_norm": 0.8864443898200989, "learning_rate": 0.0002, "epoch": 3.095823095823096, "step": 2520}, {"loss": 0.4601, "grad_norm": 0.945324718952179, "learning_rate": 0.0002, "epoch": 3.108108108108108, "step": 2530}, {"loss": 0.4345, "grad_norm": 1.0562494993209839, "learning_rate": 0.0002, "epoch": 3.1203931203931203, "step": 2540}, {"loss": 0.4375, "grad_norm": 0.8607500195503235, "learning_rate": 0.0002, "epoch": 3.1326781326781328, "step": 2550}, {"loss": 0.456, "grad_norm": 0.8719640374183655, "learning_rate": 0.0002, "epoch": 3.1449631449631448, "step": 2560}, {"loss": 0.4469, "grad_norm": 0.8647059202194214, "learning_rate": 0.0002, "epoch": 3.157248157248157, "step": 2570}, {"loss": 0.4483, "grad_norm": 0.8346507549285889, "learning_rate": 0.0002, "epoch": 3.1695331695331697, "step": 2580}, {"loss": 0.4331, "grad_norm": 1.0208854675292969, "learning_rate": 0.0002, "epoch": 3.1818181818181817, "step": 2590}, {"loss": 0.435, "grad_norm": 0.7064385414123535, "learning_rate": 0.0002, "epoch": 3.194103194103194, "step": 2600}, {"loss": 0.4541, "grad_norm": 0.927347719669342, "learning_rate": 0.0002, "epoch": 3.2063882063882065, "step": 2610}, {"loss": 0.4561, "grad_norm": 0.943517804145813, "learning_rate": 0.0002, "epoch": 3.2186732186732185, "step": 2620}, {"loss": 0.4225, "grad_norm": 0.7837198376655579, "learning_rate": 0.0002, "epoch": 3.230958230958231, "step": 2630}, {"loss": 0.4494, "grad_norm": 0.7752765417098999, "learning_rate": 0.0002, "epoch": 3.2432432432432434, "step": 2640}, {"loss": 0.4468, "grad_norm": 0.8578953146934509, "learning_rate": 0.0002, "epoch": 3.2555282555282554, "step": 2650}, {"loss": 0.4393, "grad_norm": 1.0209529399871826, "learning_rate": 0.0002, "epoch": 3.267813267813268, "step": 2660}, {"loss": 0.4517, "grad_norm": 0.9069030284881592, "learning_rate": 0.0002, "epoch": 3.2800982800982803, "step": 2670}, {"loss": 0.4262, "grad_norm": 0.8454729318618774, "learning_rate": 0.0002, "epoch": 3.2923832923832923, "step": 2680}, {"loss": 0.4349, "grad_norm": 0.8253099322319031, "learning_rate": 0.0002, "epoch": 3.3046683046683047, "step": 2690}, {"loss": 0.4503, "grad_norm": 0.8765934109687805, "learning_rate": 0.0002, "epoch": 3.3169533169533167, "step": 2700}, {"loss": 0.4518, "grad_norm": 0.8149126172065735, "learning_rate": 0.0002, "epoch": 3.329238329238329, "step": 2710}, {"loss": 0.4437, "grad_norm": 0.8820102214813232, "learning_rate": 0.0002, "epoch": 3.3415233415233416, "step": 2720}, {"loss": 0.4346, "grad_norm": 0.8813952803611755, "learning_rate": 0.0002, "epoch": 3.3538083538083536, "step": 2730}, {"loss": 0.4396, "grad_norm": 1.0338447093963623, "learning_rate": 0.0002, "epoch": 3.366093366093366, "step": 2740}, {"loss": 0.4468, "grad_norm": 0.8780209422111511, "learning_rate": 0.0002, "epoch": 3.3783783783783785, "step": 2750}, {"loss": 0.441, "grad_norm": 0.9017151594161987, "learning_rate": 0.0002, "epoch": 3.3906633906633905, "step": 2760}, {"loss": 0.446, "grad_norm": 0.8647638559341431, "learning_rate": 0.0002, "epoch": 3.402948402948403, "step": 2770}, {"loss": 0.4131, "grad_norm": 0.8298183679580688, "learning_rate": 0.0002, "epoch": 3.4152334152334154, "step": 2780}, {"loss": 0.4406, "grad_norm": 0.9298108816146851, "learning_rate": 0.0002, "epoch": 3.4275184275184274, "step": 2790}, {"loss": 0.4145, "grad_norm": 0.8909980058670044, "learning_rate": 0.0002, "epoch": 3.43980343980344, "step": 2800}, {"loss": 0.4148, "grad_norm": 0.8027496933937073, "learning_rate": 0.0002, "epoch": 3.4520884520884523, "step": 2810}, {"loss": 0.4244, "grad_norm": 0.8766195774078369, "learning_rate": 0.0002, "epoch": 3.4643734643734643, "step": 2820}, {"loss": 0.4292, "grad_norm": 0.8194443583488464, "learning_rate": 0.0002, "epoch": 3.4766584766584767, "step": 2830}, {"loss": 0.4305, "grad_norm": 0.9862873554229736, "learning_rate": 0.0002, "epoch": 3.488943488943489, "step": 2840}, {"loss": 0.4393, "grad_norm": 0.8755377531051636, "learning_rate": 0.0002, "epoch": 3.501228501228501, "step": 2850}, {"loss": 0.4231, "grad_norm": 0.7300266027450562, "learning_rate": 0.0002, "epoch": 3.5135135135135136, "step": 2860}, {"loss": 0.4278, "grad_norm": 0.8342461585998535, "learning_rate": 0.0002, "epoch": 3.5257985257985256, "step": 2870}, {"loss": 0.4395, "grad_norm": 0.8624151349067688, "learning_rate": 0.0002, "epoch": 3.538083538083538, "step": 2880}, {"loss": 0.4064, "grad_norm": 0.8931261301040649, "learning_rate": 0.0002, "epoch": 3.5503685503685505, "step": 2890}, {"loss": 0.4358, "grad_norm": 0.8617086410522461, "learning_rate": 0.0002, "epoch": 3.562653562653563, "step": 2900}, {"loss": 0.419, "grad_norm": 0.8754099607467651, "learning_rate": 0.0002, "epoch": 3.574938574938575, "step": 2910}, {"loss": 0.4275, "grad_norm": 0.8345834612846375, "learning_rate": 0.0002, "epoch": 3.5872235872235874, "step": 2920}, {"loss": 0.4375, "grad_norm": 1.1414062976837158, "learning_rate": 0.0002, "epoch": 3.5995085995085994, "step": 2930}, {"loss": 0.4297, "grad_norm": 0.994860053062439, "learning_rate": 0.0002, "epoch": 3.611793611793612, "step": 2940}, {"loss": 0.4386, "grad_norm": 1.19268000125885, "learning_rate": 0.0002, "epoch": 3.6240786240786242, "step": 2950}, {"loss": 0.4029, "grad_norm": 0.8399543762207031, "learning_rate": 0.0002, "epoch": 3.6363636363636362, "step": 2960}, {"loss": 0.4432, "grad_norm": 0.9873217940330505, "learning_rate": 0.0002, "epoch": 3.6486486486486487, "step": 2970}, {"loss": 0.4308, "grad_norm": 0.9116013646125793, "learning_rate": 0.0002, "epoch": 3.6609336609336607, "step": 2980}, {"loss": 0.4275, "grad_norm": 0.9503833651542664, "learning_rate": 0.0002, "epoch": 3.673218673218673, "step": 2990}, {"loss": 0.4306, "grad_norm": 0.9401112794876099, "learning_rate": 0.0002, "epoch": 3.6855036855036856, "step": 3000}, {"loss": 0.4333, "grad_norm": 1.00745689868927, "learning_rate": 0.0002, "epoch": 3.697788697788698, "step": 3010}, {"loss": 0.432, "grad_norm": 1.0553191900253296, "learning_rate": 0.0002, "epoch": 3.71007371007371, "step": 3020}, {"loss": 0.4321, "grad_norm": 1.0226953029632568, "learning_rate": 0.0002, "epoch": 3.7223587223587224, "step": 3030}, {"loss": 0.418, "grad_norm": 1.085554838180542, "learning_rate": 0.0002, "epoch": 3.7346437346437344, "step": 3040}, {"loss": 0.4196, "grad_norm": 0.9948731064796448, "learning_rate": 0.0002, "epoch": 3.746928746928747, "step": 3050}, {"loss": 0.4281, "grad_norm": 0.9328727126121521, "learning_rate": 0.0002, "epoch": 3.7592137592137593, "step": 3060}, {"loss": 0.4284, "grad_norm": 1.0533266067504883, "learning_rate": 0.0002, "epoch": 3.7714987714987718, "step": 3070}, {"loss": 0.4414, "grad_norm": 0.8213809132575989, "learning_rate": 0.0002, "epoch": 3.7837837837837838, "step": 3080}, {"loss": 0.4348, "grad_norm": 0.8941594362258911, "learning_rate": 0.0002, "epoch": 3.796068796068796, "step": 3090}, {"loss": 0.4266, "grad_norm": 0.8324518203735352, "learning_rate": 0.0002, "epoch": 3.808353808353808, "step": 3100}, {"loss": 0.4227, "grad_norm": 0.8811233639717102, "learning_rate": 0.0002, "epoch": 3.8206388206388207, "step": 3110}, {"loss": 0.4195, "grad_norm": 0.8781470060348511, "learning_rate": 0.0002, "epoch": 3.832923832923833, "step": 3120}, {"loss": 0.4277, "grad_norm": 0.8994116187095642, "learning_rate": 0.0002, "epoch": 3.845208845208845, "step": 3130}, {"loss": 0.4149, "grad_norm": 0.8605017066001892, "learning_rate": 0.0002, "epoch": 3.8574938574938575, "step": 3140}, {"loss": 0.4023, "grad_norm": 0.8966400027275085, "learning_rate": 0.0002, "epoch": 3.8697788697788695, "step": 3150}, {"loss": 0.4245, "grad_norm": 0.8856554627418518, "learning_rate": 0.0002, "epoch": 3.882063882063882, "step": 3160}, {"loss": 0.4101, "grad_norm": 0.8971620798110962, "learning_rate": 0.0002, "epoch": 3.8943488943488944, "step": 3170}, {"loss": 0.3993, "grad_norm": 0.9807813167572021, "learning_rate": 0.0002, "epoch": 3.906633906633907, "step": 3180}, {"loss": 0.4258, "grad_norm": 0.8614121675491333, "learning_rate": 0.0002, "epoch": 3.918918918918919, "step": 3190}, {"loss": 0.4115, "grad_norm": 0.989171028137207, "learning_rate": 0.0002, "epoch": 3.9312039312039313, "step": 3200}, {"loss": 0.4182, "grad_norm": 0.8168872594833374, "learning_rate": 0.0002, "epoch": 3.9434889434889433, "step": 3210}, {"loss": 0.4112, "grad_norm": 0.8109386563301086, "learning_rate": 0.0002, "epoch": 3.9557739557739557, "step": 3220}, {"loss": 0.4165, "grad_norm": 1.0175853967666626, "learning_rate": 0.0002, "epoch": 3.968058968058968, "step": 3230}, {"loss": 0.4146, "grad_norm": 0.936143159866333, "learning_rate": 0.0002, "epoch": 3.98034398034398, "step": 3240}, {"loss": 0.4163, "grad_norm": 0.9557915925979614, "learning_rate": 0.0002, "epoch": 3.9926289926289926, "step": 3250}, {"eval_loss": 0.4401616156101227, "eval_runtime": 20.8047, "eval_samples_per_second": 15.91, "eval_steps_per_second": 2.019, "epoch": 4.0, "step": 3256}, {"loss": 0.408, "grad_norm": 0.7590614557266235, "learning_rate": 0.0002, "epoch": 4.004914004914005, "step": 3260}, {"loss": 0.4001, "grad_norm": 0.8920791149139404, "learning_rate": 0.0002, "epoch": 4.017199017199017, "step": 3270}, {"loss": 0.3789, "grad_norm": 0.8640421628952026, "learning_rate": 0.0002, "epoch": 4.0294840294840295, "step": 3280}, {"loss": 0.3791, "grad_norm": 0.9074113965034485, "learning_rate": 0.0002, "epoch": 4.041769041769042, "step": 3290}, {"loss": 0.3728, "grad_norm": 1.0600885152816772, "learning_rate": 0.0002, "epoch": 4.054054054054054, "step": 3300}, {"loss": 0.3857, "grad_norm": 0.9682773351669312, "learning_rate": 0.0002, "epoch": 4.066339066339066, "step": 3310}, {"loss": 0.4007, "grad_norm": 0.9326395392417908, "learning_rate": 0.0002, "epoch": 4.078624078624078, "step": 3320}, {"loss": 0.3823, "grad_norm": 0.8886597156524658, "learning_rate": 0.0002, "epoch": 4.090909090909091, "step": 3330}, {"loss": 0.3929, "grad_norm": 1.032205581665039, "learning_rate": 0.0002, "epoch": 4.103194103194103, "step": 3340}, {"loss": 0.3836, "grad_norm": 0.8669408559799194, "learning_rate": 0.0002, "epoch": 4.115479115479116, "step": 3350}, {"loss": 0.3866, "grad_norm": 0.8250347971916199, "learning_rate": 0.0002, "epoch": 4.127764127764128, "step": 3360}, {"loss": 0.3826, "grad_norm": 0.7919842600822449, "learning_rate": 0.0002, "epoch": 4.14004914004914, "step": 3370}, {"loss": 0.3838, "grad_norm": 1.045682430267334, "learning_rate": 0.0002, "epoch": 4.152334152334152, "step": 3380}, {"loss": 0.3796, "grad_norm": 0.6873571276664734, "learning_rate": 0.0002, "epoch": 4.164619164619165, "step": 3390}, {"loss": 0.3942, "grad_norm": 1.0227675437927246, "learning_rate": 0.0002, "epoch": 4.176904176904177, "step": 3400}, {"loss": 0.3788, "grad_norm": 0.9167711734771729, "learning_rate": 0.0002, "epoch": 4.1891891891891895, "step": 3410}, {"loss": 0.3792, "grad_norm": 1.0598796606063843, "learning_rate": 0.0002, "epoch": 4.201474201474202, "step": 3420}, {"loss": 0.3955, "grad_norm": 0.8581843972206116, "learning_rate": 0.0002, "epoch": 4.2137592137592135, "step": 3430}, {"loss": 0.3761, "grad_norm": 0.8862360119819641, "learning_rate": 0.0002, "epoch": 4.226044226044226, "step": 3440}, {"loss": 0.3889, "grad_norm": 1.0248323678970337, "learning_rate": 0.0002, "epoch": 4.238329238329238, "step": 3450}, {"loss": 0.3827, "grad_norm": 0.8746261596679688, "learning_rate": 0.0002, "epoch": 4.250614250614251, "step": 3460}, {"loss": 0.3949, "grad_norm": 0.7442536354064941, "learning_rate": 0.0002, "epoch": 4.262899262899263, "step": 3470}, {"loss": 0.3761, "grad_norm": 0.8295119404792786, "learning_rate": 0.0002, "epoch": 4.275184275184275, "step": 3480}, {"loss": 0.3895, "grad_norm": 1.0634245872497559, "learning_rate": 0.0002, "epoch": 4.287469287469287, "step": 3490}, {"loss": 0.3955, "grad_norm": 0.9554621577262878, "learning_rate": 0.0002, "epoch": 4.2997542997543, "step": 3500}, {"loss": 0.3826, "grad_norm": 1.0191723108291626, "learning_rate": 0.0002, "epoch": 4.312039312039312, "step": 3510}, {"loss": 0.3828, "grad_norm": 0.8573611378669739, "learning_rate": 0.0002, "epoch": 4.324324324324325, "step": 3520}, {"loss": 0.3869, "grad_norm": 0.9082390069961548, "learning_rate": 0.0002, "epoch": 4.336609336609337, "step": 3530}, {"loss": 0.3902, "grad_norm": 0.8650212287902832, "learning_rate": 0.0002, "epoch": 4.348894348894349, "step": 3540}, {"loss": 0.3915, "grad_norm": 0.7186297178268433, "learning_rate": 0.0002, "epoch": 4.361179361179361, "step": 3550}, {"loss": 0.3861, "grad_norm": 0.9750986695289612, "learning_rate": 0.0002, "epoch": 4.3734643734643734, "step": 3560}, {"loss": 0.3967, "grad_norm": 1.0710467100143433, "learning_rate": 0.0002, "epoch": 4.385749385749386, "step": 3570}, {"loss": 0.3774, "grad_norm": 0.7974869012832642, "learning_rate": 0.0002, "epoch": 4.398034398034398, "step": 3580}, {"loss": 0.3738, "grad_norm": 0.9405913949012756, "learning_rate": 0.0002, "epoch": 4.41031941031941, "step": 3590}, {"loss": 0.3982, "grad_norm": 0.9393602609634399, "learning_rate": 0.0002, "epoch": 4.422604422604422, "step": 3600}, {"loss": 0.3913, "grad_norm": 1.0798007249832153, "learning_rate": 0.0002, "epoch": 4.434889434889435, "step": 3610}, {"loss": 0.3682, "grad_norm": 0.9226186275482178, "learning_rate": 0.0002, "epoch": 4.447174447174447, "step": 3620}, {"loss": 0.3742, "grad_norm": 1.1046524047851562, "learning_rate": 0.0002, "epoch": 4.45945945945946, "step": 3630}, {"loss": 0.3886, "grad_norm": 0.8848567605018616, "learning_rate": 0.0002, "epoch": 4.471744471744472, "step": 3640}, {"loss": 0.3848, "grad_norm": 0.8913224339485168, "learning_rate": 0.0002, "epoch": 4.484029484029484, "step": 3650}, {"loss": 0.3731, "grad_norm": 0.8497583270072937, "learning_rate": 0.0002, "epoch": 4.496314496314496, "step": 3660}, {"loss": 0.3804, "grad_norm": 0.8263831734657288, "learning_rate": 0.0002, "epoch": 4.5085995085995085, "step": 3670}, {"loss": 0.3815, "grad_norm": 0.8470269441604614, "learning_rate": 0.0002, "epoch": 4.520884520884521, "step": 3680}, {"loss": 0.3774, "grad_norm": 0.860038161277771, "learning_rate": 0.0002, "epoch": 4.533169533169533, "step": 3690}, {"loss": 0.3817, "grad_norm": 0.8898552656173706, "learning_rate": 0.0002, "epoch": 4.545454545454545, "step": 3700}, {"loss": 0.3776, "grad_norm": 0.8152070641517639, "learning_rate": 0.0002, "epoch": 4.557739557739557, "step": 3710}, {"loss": 0.383, "grad_norm": 0.7847675085067749, "learning_rate": 0.0002, "epoch": 4.57002457002457, "step": 3720}, {"loss": 0.3791, "grad_norm": 0.9625533819198608, "learning_rate": 0.0002, "epoch": 4.582309582309582, "step": 3730}, {"loss": 0.3699, "grad_norm": 0.9097456336021423, "learning_rate": 0.0002, "epoch": 4.594594594594595, "step": 3740}, {"loss": 0.3673, "grad_norm": 0.871329128742218, "learning_rate": 0.0002, "epoch": 4.606879606879607, "step": 3750}, {"loss": 0.3725, "grad_norm": 0.9879975914955139, "learning_rate": 0.0002, "epoch": 4.61916461916462, "step": 3760}, {"loss": 0.3827, "grad_norm": 0.8636731505393982, "learning_rate": 0.0002, "epoch": 4.631449631449631, "step": 3770}, {"loss": 0.3755, "grad_norm": 1.0488964319229126, "learning_rate": 0.0002, "epoch": 4.643734643734644, "step": 3780}, {"loss": 0.3738, "grad_norm": 0.7637056112289429, "learning_rate": 0.0002, "epoch": 4.656019656019656, "step": 3790}, {"loss": 0.3676, "grad_norm": 0.8507546186447144, "learning_rate": 0.0002, "epoch": 4.6683046683046685, "step": 3800}, {"loss": 0.3852, "grad_norm": 1.0216856002807617, "learning_rate": 0.0002, "epoch": 4.680589680589681, "step": 3810}, {"loss": 0.3751, "grad_norm": 1.026343822479248, "learning_rate": 0.0002, "epoch": 4.6928746928746925, "step": 3820}, {"loss": 0.3687, "grad_norm": 0.8311620950698853, "learning_rate": 0.0002, "epoch": 4.705159705159705, "step": 3830}, {"loss": 0.3771, "grad_norm": 0.7770653367042542, "learning_rate": 0.0002, "epoch": 4.717444717444717, "step": 3840}, {"loss": 0.37, "grad_norm": 0.7616215348243713, "learning_rate": 0.0002, "epoch": 4.72972972972973, "step": 3850}, {"loss": 0.3927, "grad_norm": 1.0377072095870972, "learning_rate": 0.0002, "epoch": 4.742014742014742, "step": 3860}, {"loss": 0.3832, "grad_norm": 0.9713505506515503, "learning_rate": 0.0002, "epoch": 4.754299754299755, "step": 3870}, {"loss": 0.3722, "grad_norm": 0.8803321719169617, "learning_rate": 0.0002, "epoch": 4.766584766584766, "step": 3880}, {"loss": 0.3756, "grad_norm": 0.885535478591919, "learning_rate": 0.0002, "epoch": 4.778869778869779, "step": 3890}, {"loss": 0.3714, "grad_norm": 1.0877983570098877, "learning_rate": 0.0002, "epoch": 4.791154791154791, "step": 3900}, {"loss": 0.3879, "grad_norm": 0.7875366806983948, "learning_rate": 0.0002, "epoch": 4.803439803439804, "step": 3910}, {"loss": 0.3591, "grad_norm": 0.8550102114677429, "learning_rate": 0.0002, "epoch": 4.815724815724816, "step": 3920}, {"loss": 0.3716, "grad_norm": 1.0217846632003784, "learning_rate": 0.0002, "epoch": 4.828009828009828, "step": 3930}, {"loss": 0.3649, "grad_norm": 0.7315713167190552, "learning_rate": 0.0002, "epoch": 4.84029484029484, "step": 3940}, {"loss": 0.3879, "grad_norm": 0.8924923539161682, "learning_rate": 0.0002, "epoch": 4.8525798525798525, "step": 3950}, {"loss": 0.3669, "grad_norm": 0.9730218052864075, "learning_rate": 0.0002, "epoch": 4.864864864864865, "step": 3960}, {"loss": 0.3705, "grad_norm": 0.9202003479003906, "learning_rate": 0.0002, "epoch": 4.877149877149877, "step": 3970}, {"loss": 0.3617, "grad_norm": 0.8173081874847412, "learning_rate": 0.0002, "epoch": 4.88943488943489, "step": 3980}, {"loss": 0.37, "grad_norm": 0.7178564667701721, "learning_rate": 0.0002, "epoch": 4.901719901719901, "step": 3990}, {"loss": 0.3768, "grad_norm": 0.913684606552124, "learning_rate": 0.0002, "epoch": 4.914004914004914, "step": 4000}, {"loss": 0.3755, "grad_norm": 0.8817896842956543, "learning_rate": 0.0002, "epoch": 4.926289926289926, "step": 4010}, {"loss": 0.3676, "grad_norm": 0.7652186751365662, "learning_rate": 0.0002, "epoch": 4.938574938574939, "step": 4020}, {"loss": 0.3699, "grad_norm": 0.8828630447387695, "learning_rate": 0.0002, "epoch": 4.950859950859951, "step": 4030}, {"loss": 0.3672, "grad_norm": 1.0878605842590332, "learning_rate": 0.0002, "epoch": 4.963144963144963, "step": 4040}, {"loss": 0.3656, "grad_norm": 1.0845288038253784, "learning_rate": 0.0002, "epoch": 4.975429975429975, "step": 4050}, {"loss": 0.365, "grad_norm": 0.8431115746498108, "learning_rate": 0.0002, "epoch": 4.987714987714988, "step": 4060}, {"loss": 0.3693, "grad_norm": 0.8320387601852417, "learning_rate": 0.0002, "epoch": 5.0, "step": 4070}]}
+{"epoch": 6.0, "step": 4884, "epoch_duration": 781.9419949054718, "total_accumulated_duration": 4492.765958547592, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4070", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}, {"eval_loss": 0.49752503633499146, "eval_runtime": 20.2911, "eval_samples_per_second": 16.313, "eval_steps_per_second": 2.07, "epoch": 3.0, "step": 2442}, {"loss": 0.4362, "grad_norm": 0.7644656896591187, "learning_rate": 0.0002, "epoch": 3.0098280098280097, "step": 2450}, {"loss": 0.4363, "grad_norm": 0.9077525734901428, "learning_rate": 0.0002, "epoch": 3.022113022113022, "step": 2460}, {"loss": 0.422, "grad_norm": 0.7859287261962891, "learning_rate": 0.0002, "epoch": 3.0343980343980346, "step": 2470}, {"loss": 0.4574, "grad_norm": 1.1200323104858398, "learning_rate": 0.0002, "epoch": 3.0466830466830466, "step": 2480}, {"loss": 0.4519, "grad_norm": 0.7570453882217407, "learning_rate": 0.0002, "epoch": 3.058968058968059, "step": 2490}, {"loss": 0.4351, "grad_norm": 0.9450915455818176, "learning_rate": 0.0002, "epoch": 3.0712530712530715, "step": 2500}, {"loss": 0.4343, "grad_norm": 0.8303545117378235, "learning_rate": 0.0002, "epoch": 3.0835380835380835, "step": 2510}, {"loss": 0.4308, "grad_norm": 0.8864443898200989, "learning_rate": 0.0002, "epoch": 3.095823095823096, "step": 2520}, {"loss": 0.4601, "grad_norm": 0.945324718952179, "learning_rate": 0.0002, "epoch": 3.108108108108108, "step": 2530}, {"loss": 0.4345, "grad_norm": 1.0562494993209839, "learning_rate": 0.0002, "epoch": 3.1203931203931203, "step": 2540}, {"loss": 0.4375, "grad_norm": 0.8607500195503235, "learning_rate": 0.0002, "epoch": 3.1326781326781328, "step": 2550}, {"loss": 0.456, "grad_norm": 0.8719640374183655, "learning_rate": 0.0002, "epoch": 3.1449631449631448, "step": 2560}, {"loss": 0.4469, "grad_norm": 0.8647059202194214, "learning_rate": 0.0002, "epoch": 3.157248157248157, "step": 2570}, {"loss": 0.4483, "grad_norm": 0.8346507549285889, "learning_rate": 0.0002, "epoch": 3.1695331695331697, "step": 2580}, {"loss": 0.4331, "grad_norm": 1.0208854675292969, "learning_rate": 0.0002, "epoch": 3.1818181818181817, "step": 2590}, {"loss": 0.435, "grad_norm": 0.7064385414123535, "learning_rate": 0.0002, "epoch": 3.194103194103194, "step": 2600}, {"loss": 0.4541, "grad_norm": 0.927347719669342, "learning_rate": 0.0002, "epoch": 3.2063882063882065, "step": 2610}, {"loss": 0.4561, "grad_norm": 0.943517804145813, "learning_rate": 0.0002, "epoch": 3.2186732186732185, "step": 2620}, {"loss": 0.4225, "grad_norm": 0.7837198376655579, "learning_rate": 0.0002, "epoch": 3.230958230958231, "step": 2630}, {"loss": 0.4494, "grad_norm": 0.7752765417098999, "learning_rate": 0.0002, "epoch": 3.2432432432432434, "step": 2640}, {"loss": 0.4468, "grad_norm": 0.8578953146934509, "learning_rate": 0.0002, "epoch": 3.2555282555282554, "step": 2650}, {"loss": 0.4393, "grad_norm": 1.0209529399871826, "learning_rate": 0.0002, "epoch": 3.267813267813268, "step": 2660}, {"loss": 0.4517, "grad_norm": 0.9069030284881592, "learning_rate": 0.0002, "epoch": 3.2800982800982803, "step": 2670}, {"loss": 0.4262, "grad_norm": 0.8454729318618774, "learning_rate": 0.0002, "epoch": 3.2923832923832923, "step": 2680}, {"loss": 0.4349, "grad_norm": 0.8253099322319031, "learning_rate": 0.0002, "epoch": 3.3046683046683047, "step": 2690}, {"loss": 0.4503, "grad_norm": 0.8765934109687805, "learning_rate": 0.0002, "epoch": 3.3169533169533167, "step": 2700}, {"loss": 0.4518, "grad_norm": 0.8149126172065735, "learning_rate": 0.0002, "epoch": 3.329238329238329, "step": 2710}, {"loss": 0.4437, "grad_norm": 0.8820102214813232, "learning_rate": 0.0002, "epoch": 3.3415233415233416, "step": 2720}, {"loss": 0.4346, "grad_norm": 0.8813952803611755, "learning_rate": 0.0002, "epoch": 3.3538083538083536, "step": 2730}, {"loss": 0.4396, "grad_norm": 1.0338447093963623, "learning_rate": 0.0002, "epoch": 3.366093366093366, "step": 2740}, {"loss": 0.4468, "grad_norm": 0.8780209422111511, "learning_rate": 0.0002, "epoch": 3.3783783783783785, "step": 2750}, {"loss": 0.441, "grad_norm": 0.9017151594161987, "learning_rate": 0.0002, "epoch": 3.3906633906633905, "step": 2760}, {"loss": 0.446, "grad_norm": 0.8647638559341431, "learning_rate": 0.0002, "epoch": 3.402948402948403, "step": 2770}, {"loss": 0.4131, "grad_norm": 0.8298183679580688, "learning_rate": 0.0002, "epoch": 3.4152334152334154, "step": 2780}, {"loss": 0.4406, "grad_norm": 0.9298108816146851, "learning_rate": 0.0002, "epoch": 3.4275184275184274, "step": 2790}, {"loss": 0.4145, "grad_norm": 0.8909980058670044, "learning_rate": 0.0002, "epoch": 3.43980343980344, "step": 2800}, {"loss": 0.4148, "grad_norm": 0.8027496933937073, "learning_rate": 0.0002, "epoch": 3.4520884520884523, "step": 2810}, {"loss": 0.4244, "grad_norm": 0.8766195774078369, "learning_rate": 0.0002, "epoch": 3.4643734643734643, "step": 2820}, {"loss": 0.4292, "grad_norm": 0.8194443583488464, "learning_rate": 0.0002, "epoch": 3.4766584766584767, "step": 2830}, {"loss": 0.4305, "grad_norm": 0.9862873554229736, "learning_rate": 0.0002, "epoch": 3.488943488943489, "step": 2840}, {"loss": 0.4393, "grad_norm": 0.8755377531051636, "learning_rate": 0.0002, "epoch": 3.501228501228501, "step": 2850}, {"loss": 0.4231, "grad_norm": 0.7300266027450562, "learning_rate": 0.0002, "epoch": 3.5135135135135136, "step": 2860}, {"loss": 0.4278, "grad_norm": 0.8342461585998535, "learning_rate": 0.0002, "epoch": 3.5257985257985256, "step": 2870}, {"loss": 0.4395, "grad_norm": 0.8624151349067688, "learning_rate": 0.0002, "epoch": 3.538083538083538, "step": 2880}, {"loss": 0.4064, "grad_norm": 0.8931261301040649, "learning_rate": 0.0002, "epoch": 3.5503685503685505, "step": 2890}, {"loss": 0.4358, "grad_norm": 0.8617086410522461, "learning_rate": 0.0002, "epoch": 3.562653562653563, "step": 2900}, {"loss": 0.419, "grad_norm": 0.8754099607467651, "learning_rate": 0.0002, "epoch": 3.574938574938575, "step": 2910}, {"loss": 0.4275, "grad_norm": 0.8345834612846375, "learning_rate": 0.0002, "epoch": 3.5872235872235874, "step": 2920}, {"loss": 0.4375, "grad_norm": 1.1414062976837158, "learning_rate": 0.0002, "epoch": 3.5995085995085994, "step": 2930}, {"loss": 0.4297, "grad_norm": 0.994860053062439, "learning_rate": 0.0002, "epoch": 3.611793611793612, "step": 2940}, {"loss": 0.4386, "grad_norm": 1.19268000125885, "learning_rate": 0.0002, "epoch": 3.6240786240786242, "step": 2950}, {"loss": 0.4029, "grad_norm": 0.8399543762207031, "learning_rate": 0.0002, "epoch": 3.6363636363636362, "step": 2960}, {"loss": 0.4432, "grad_norm": 0.9873217940330505, "learning_rate": 0.0002, "epoch": 3.6486486486486487, "step": 2970}, {"loss": 0.4308, "grad_norm": 0.9116013646125793, "learning_rate": 0.0002, "epoch": 3.6609336609336607, "step": 2980}, {"loss": 0.4275, "grad_norm": 0.9503833651542664, "learning_rate": 0.0002, "epoch": 3.673218673218673, "step": 2990}, {"loss": 0.4306, "grad_norm": 0.9401112794876099, "learning_rate": 0.0002, "epoch": 3.6855036855036856, "step": 3000}, {"loss": 0.4333, "grad_norm": 1.00745689868927, "learning_rate": 0.0002, "epoch": 3.697788697788698, "step": 3010}, {"loss": 0.432, "grad_norm": 1.0553191900253296, "learning_rate": 0.0002, "epoch": 3.71007371007371, "step": 3020}, {"loss": 0.4321, "grad_norm": 1.0226953029632568, "learning_rate": 0.0002, "epoch": 3.7223587223587224, "step": 3030}, {"loss": 0.418, "grad_norm": 1.085554838180542, "learning_rate": 0.0002, "epoch": 3.7346437346437344, "step": 3040}, {"loss": 0.4196, "grad_norm": 0.9948731064796448, "learning_rate": 0.0002, "epoch": 3.746928746928747, "step": 3050}, {"loss": 0.4281, "grad_norm": 0.9328727126121521, "learning_rate": 0.0002, "epoch": 3.7592137592137593, "step": 3060}, {"loss": 0.4284, "grad_norm": 1.0533266067504883, "learning_rate": 0.0002, "epoch": 3.7714987714987718, "step": 3070}, {"loss": 0.4414, "grad_norm": 0.8213809132575989, "learning_rate": 0.0002, "epoch": 3.7837837837837838, "step": 3080}, {"loss": 0.4348, "grad_norm": 0.8941594362258911, "learning_rate": 0.0002, "epoch": 3.796068796068796, "step": 3090}, {"loss": 0.4266, "grad_norm": 0.8324518203735352, "learning_rate": 0.0002, "epoch": 3.808353808353808, "step": 3100}, {"loss": 0.4227, "grad_norm": 0.8811233639717102, "learning_rate": 0.0002, "epoch": 3.8206388206388207, "step": 3110}, {"loss": 0.4195, "grad_norm": 0.8781470060348511, "learning_rate": 0.0002, "epoch": 3.832923832923833, "step": 3120}, {"loss": 0.4277, "grad_norm": 0.8994116187095642, "learning_rate": 0.0002, "epoch": 3.845208845208845, "step": 3130}, {"loss": 0.4149, "grad_norm": 0.8605017066001892, "learning_rate": 0.0002, "epoch": 3.8574938574938575, "step": 3140}, {"loss": 0.4023, "grad_norm": 0.8966400027275085, "learning_rate": 0.0002, "epoch": 3.8697788697788695, "step": 3150}, {"loss": 0.4245, "grad_norm": 0.8856554627418518, "learning_rate": 0.0002, "epoch": 3.882063882063882, "step": 3160}, {"loss": 0.4101, "grad_norm": 0.8971620798110962, "learning_rate": 0.0002, "epoch": 3.8943488943488944, "step": 3170}, {"loss": 0.3993, "grad_norm": 0.9807813167572021, "learning_rate": 0.0002, "epoch": 3.906633906633907, "step": 3180}, {"loss": 0.4258, "grad_norm": 0.8614121675491333, "learning_rate": 0.0002, "epoch": 3.918918918918919, "step": 3190}, {"loss": 0.4115, "grad_norm": 0.989171028137207, "learning_rate": 0.0002, "epoch": 3.9312039312039313, "step": 3200}, {"loss": 0.4182, "grad_norm": 0.8168872594833374, "learning_rate": 0.0002, "epoch": 3.9434889434889433, "step": 3210}, {"loss": 0.4112, "grad_norm": 0.8109386563301086, "learning_rate": 0.0002, "epoch": 3.9557739557739557, "step": 3220}, {"loss": 0.4165, "grad_norm": 1.0175853967666626, "learning_rate": 0.0002, "epoch": 3.968058968058968, "step": 3230}, {"loss": 0.4146, "grad_norm": 0.936143159866333, "learning_rate": 0.0002, "epoch": 3.98034398034398, "step": 3240}, {"loss": 0.4163, "grad_norm": 0.9557915925979614, "learning_rate": 0.0002, "epoch": 3.9926289926289926, "step": 3250}, {"eval_loss": 0.4401616156101227, "eval_runtime": 20.8047, "eval_samples_per_second": 15.91, "eval_steps_per_second": 2.019, "epoch": 4.0, "step": 3256}, {"loss": 0.408, "grad_norm": 0.7590614557266235, "learning_rate": 0.0002, "epoch": 4.004914004914005, "step": 3260}, {"loss": 0.4001, "grad_norm": 0.8920791149139404, "learning_rate": 0.0002, "epoch": 4.017199017199017, "step": 3270}, {"loss": 0.3789, "grad_norm": 0.8640421628952026, "learning_rate": 0.0002, "epoch": 4.0294840294840295, "step": 3280}, {"loss": 0.3791, "grad_norm": 0.9074113965034485, "learning_rate": 0.0002, "epoch": 4.041769041769042, "step": 3290}, {"loss": 0.3728, "grad_norm": 1.0600885152816772, "learning_rate": 0.0002, "epoch": 4.054054054054054, "step": 3300}, {"loss": 0.3857, "grad_norm": 0.9682773351669312, "learning_rate": 0.0002, "epoch": 4.066339066339066, "step": 3310}, {"loss": 0.4007, "grad_norm": 0.9326395392417908, "learning_rate": 0.0002, "epoch": 4.078624078624078, "step": 3320}, {"loss": 0.3823, "grad_norm": 0.8886597156524658, "learning_rate": 0.0002, "epoch": 4.090909090909091, "step": 3330}, {"loss": 0.3929, "grad_norm": 1.032205581665039, "learning_rate": 0.0002, "epoch": 4.103194103194103, "step": 3340}, {"loss": 0.3836, "grad_norm": 0.8669408559799194, "learning_rate": 0.0002, "epoch": 4.115479115479116, "step": 3350}, {"loss": 0.3866, "grad_norm": 0.8250347971916199, "learning_rate": 0.0002, "epoch": 4.127764127764128, "step": 3360}, {"loss": 0.3826, "grad_norm": 0.7919842600822449, "learning_rate": 0.0002, "epoch": 4.14004914004914, "step": 3370}, {"loss": 0.3838, "grad_norm": 1.045682430267334, "learning_rate": 0.0002, "epoch": 4.152334152334152, "step": 3380}, {"loss": 0.3796, "grad_norm": 0.6873571276664734, "learning_rate": 0.0002, "epoch": 4.164619164619165, "step": 3390}, {"loss": 0.3942, "grad_norm": 1.0227675437927246, "learning_rate": 0.0002, "epoch": 4.176904176904177, "step": 3400}, {"loss": 0.3788, "grad_norm": 0.9167711734771729, "learning_rate": 0.0002, "epoch": 4.1891891891891895, "step": 3410}, {"loss": 0.3792, "grad_norm": 1.0598796606063843, "learning_rate": 0.0002, "epoch": 4.201474201474202, "step": 3420}, {"loss": 0.3955, "grad_norm": 0.8581843972206116, "learning_rate": 0.0002, "epoch": 4.2137592137592135, "step": 3430}, {"loss": 0.3761, "grad_norm": 0.8862360119819641, "learning_rate": 0.0002, "epoch": 4.226044226044226, "step": 3440}, {"loss": 0.3889, "grad_norm": 1.0248323678970337, "learning_rate": 0.0002, "epoch": 4.238329238329238, "step": 3450}, {"loss": 0.3827, "grad_norm": 0.8746261596679688, "learning_rate": 0.0002, "epoch": 4.250614250614251, "step": 3460}, {"loss": 0.3949, "grad_norm": 0.7442536354064941, "learning_rate": 0.0002, "epoch": 4.262899262899263, "step": 3470}, {"loss": 0.3761, "grad_norm": 0.8295119404792786, "learning_rate": 0.0002, "epoch": 4.275184275184275, "step": 3480}, {"loss": 0.3895, "grad_norm": 1.0634245872497559, "learning_rate": 0.0002, "epoch": 4.287469287469287, "step": 3490}, {"loss": 0.3955, "grad_norm": 0.9554621577262878, "learning_rate": 0.0002, "epoch": 4.2997542997543, "step": 3500}, {"loss": 0.3826, "grad_norm": 1.0191723108291626, "learning_rate": 0.0002, "epoch": 4.312039312039312, "step": 3510}, {"loss": 0.3828, "grad_norm": 0.8573611378669739, "learning_rate": 0.0002, "epoch": 4.324324324324325, "step": 3520}, {"loss": 0.3869, "grad_norm": 0.9082390069961548, "learning_rate": 0.0002, "epoch": 4.336609336609337, "step": 3530}, {"loss": 0.3902, "grad_norm": 0.8650212287902832, "learning_rate": 0.0002, "epoch": 4.348894348894349, "step": 3540}, {"loss": 0.3915, "grad_norm": 0.7186297178268433, "learning_rate": 0.0002, "epoch": 4.361179361179361, "step": 3550}, {"loss": 0.3861, "grad_norm": 0.9750986695289612, "learning_rate": 0.0002, "epoch": 4.3734643734643734, "step": 3560}, {"loss": 0.3967, "grad_norm": 1.0710467100143433, "learning_rate": 0.0002, "epoch": 4.385749385749386, "step": 3570}, {"loss": 0.3774, "grad_norm": 0.7974869012832642, "learning_rate": 0.0002, "epoch": 4.398034398034398, "step": 3580}, {"loss": 0.3738, "grad_norm": 0.9405913949012756, "learning_rate": 0.0002, "epoch": 4.41031941031941, "step": 3590}, {"loss": 0.3982, "grad_norm": 0.9393602609634399, "learning_rate": 0.0002, "epoch": 4.422604422604422, "step": 3600}, {"loss": 0.3913, "grad_norm": 1.0798007249832153, "learning_rate": 0.0002, "epoch": 4.434889434889435, "step": 3610}, {"loss": 0.3682, "grad_norm": 0.9226186275482178, "learning_rate": 0.0002, "epoch": 4.447174447174447, "step": 3620}, {"loss": 0.3742, "grad_norm": 1.1046524047851562, "learning_rate": 0.0002, "epoch": 4.45945945945946, "step": 3630}, {"loss": 0.3886, "grad_norm": 0.8848567605018616, "learning_rate": 0.0002, "epoch": 4.471744471744472, "step": 3640}, {"loss": 0.3848, "grad_norm": 0.8913224339485168, "learning_rate": 0.0002, "epoch": 4.484029484029484, "step": 3650}, {"loss": 0.3731, "grad_norm": 0.8497583270072937, "learning_rate": 0.0002, "epoch": 4.496314496314496, "step": 3660}, {"loss": 0.3804, "grad_norm": 0.8263831734657288, "learning_rate": 0.0002, "epoch": 4.5085995085995085, "step": 3670}, {"loss": 0.3815, "grad_norm": 0.8470269441604614, "learning_rate": 0.0002, "epoch": 4.520884520884521, "step": 3680}, {"loss": 0.3774, "grad_norm": 0.860038161277771, "learning_rate": 0.0002, "epoch": 4.533169533169533, "step": 3690}, {"loss": 0.3817, "grad_norm": 0.8898552656173706, "learning_rate": 0.0002, "epoch": 4.545454545454545, "step": 3700}, {"loss": 0.3776, "grad_norm": 0.8152070641517639, "learning_rate": 0.0002, "epoch": 4.557739557739557, "step": 3710}, {"loss": 0.383, "grad_norm": 0.7847675085067749, "learning_rate": 0.0002, "epoch": 4.57002457002457, "step": 3720}, {"loss": 0.3791, "grad_norm": 0.9625533819198608, "learning_rate": 0.0002, "epoch": 4.582309582309582, "step": 3730}, {"loss": 0.3699, "grad_norm": 0.9097456336021423, "learning_rate": 0.0002, "epoch": 4.594594594594595, "step": 3740}, {"loss": 0.3673, "grad_norm": 0.871329128742218, "learning_rate": 0.0002, "epoch": 4.606879606879607, "step": 3750}, {"loss": 0.3725, "grad_norm": 0.9879975914955139, "learning_rate": 0.0002, "epoch": 4.61916461916462, "step": 3760}, {"loss": 0.3827, "grad_norm": 0.8636731505393982, "learning_rate": 0.0002, "epoch": 4.631449631449631, "step": 3770}, {"loss": 0.3755, "grad_norm": 1.0488964319229126, "learning_rate": 0.0002, "epoch": 4.643734643734644, "step": 3780}, {"loss": 0.3738, "grad_norm": 0.7637056112289429, "learning_rate": 0.0002, "epoch": 4.656019656019656, "step": 3790}, {"loss": 0.3676, "grad_norm": 0.8507546186447144, "learning_rate": 0.0002, "epoch": 4.6683046683046685, "step": 3800}, {"loss": 0.3852, "grad_norm": 1.0216856002807617, "learning_rate": 0.0002, "epoch": 4.680589680589681, "step": 3810}, {"loss": 0.3751, "grad_norm": 1.026343822479248, "learning_rate": 0.0002, "epoch": 4.6928746928746925, "step": 3820}, {"loss": 0.3687, "grad_norm": 0.8311620950698853, "learning_rate": 0.0002, "epoch": 4.705159705159705, "step": 3830}, {"loss": 0.3771, "grad_norm": 0.7770653367042542, "learning_rate": 0.0002, "epoch": 4.717444717444717, "step": 3840}, {"loss": 0.37, "grad_norm": 0.7616215348243713, "learning_rate": 0.0002, "epoch": 4.72972972972973, "step": 3850}, {"loss": 0.3927, "grad_norm": 1.0377072095870972, "learning_rate": 0.0002, "epoch": 4.742014742014742, "step": 3860}, {"loss": 0.3832, "grad_norm": 0.9713505506515503, "learning_rate": 0.0002, "epoch": 4.754299754299755, "step": 3870}, {"loss": 0.3722, "grad_norm": 0.8803321719169617, "learning_rate": 0.0002, "epoch": 4.766584766584766, "step": 3880}, {"loss": 0.3756, "grad_norm": 0.885535478591919, "learning_rate": 0.0002, "epoch": 4.778869778869779, "step": 3890}, {"loss": 0.3714, "grad_norm": 1.0877983570098877, "learning_rate": 0.0002, "epoch": 4.791154791154791, "step": 3900}, {"loss": 0.3879, "grad_norm": 0.7875366806983948, "learning_rate": 0.0002, "epoch": 4.803439803439804, "step": 3910}, {"loss": 0.3591, "grad_norm": 0.8550102114677429, "learning_rate": 0.0002, "epoch": 4.815724815724816, "step": 3920}, {"loss": 0.3716, "grad_norm": 1.0217846632003784, "learning_rate": 0.0002, "epoch": 4.828009828009828, "step": 3930}, {"loss": 0.3649, "grad_norm": 0.7315713167190552, "learning_rate": 0.0002, "epoch": 4.84029484029484, "step": 3940}, {"loss": 0.3879, "grad_norm": 0.8924923539161682, "learning_rate": 0.0002, "epoch": 4.8525798525798525, "step": 3950}, {"loss": 0.3669, "grad_norm": 0.9730218052864075, "learning_rate": 0.0002, "epoch": 4.864864864864865, "step": 3960}, {"loss": 0.3705, "grad_norm": 0.9202003479003906, "learning_rate": 0.0002, "epoch": 4.877149877149877, "step": 3970}, {"loss": 0.3617, "grad_norm": 0.8173081874847412, "learning_rate": 0.0002, "epoch": 4.88943488943489, "step": 3980}, {"loss": 0.37, "grad_norm": 0.7178564667701721, "learning_rate": 0.0002, "epoch": 4.901719901719901, "step": 3990}, {"loss": 0.3768, "grad_norm": 0.913684606552124, "learning_rate": 0.0002, "epoch": 4.914004914004914, "step": 4000}, {"loss": 0.3755, "grad_norm": 0.8817896842956543, "learning_rate": 0.0002, "epoch": 4.926289926289926, "step": 4010}, {"loss": 0.3676, "grad_norm": 0.7652186751365662, "learning_rate": 0.0002, "epoch": 4.938574938574939, "step": 4020}, {"loss": 0.3699, "grad_norm": 0.8828630447387695, "learning_rate": 0.0002, "epoch": 4.950859950859951, "step": 4030}, {"loss": 0.3672, "grad_norm": 1.0878605842590332, "learning_rate": 0.0002, "epoch": 4.963144963144963, "step": 4040}, {"loss": 0.3656, "grad_norm": 1.0845288038253784, "learning_rate": 0.0002, "epoch": 4.975429975429975, "step": 4050}, {"loss": 0.365, "grad_norm": 0.8431115746498108, "learning_rate": 0.0002, "epoch": 4.987714987714988, "step": 4060}, {"loss": 0.3693, "grad_norm": 0.8320387601852417, "learning_rate": 0.0002, "epoch": 5.0, "step": 4070}, {"eval_loss": 0.4017423093318939, "eval_runtime": 20.8466, "eval_samples_per_second": 15.878, "eval_steps_per_second": 2.015, "epoch": 5.0, "step": 4070}, {"loss": 0.3425, "grad_norm": 0.8639023900032043, "learning_rate": 0.0002, "epoch": 5.012285012285012, "step": 4080}, {"loss": 0.3458, "grad_norm": 0.7123713493347168, "learning_rate": 0.0002, "epoch": 5.024570024570025, "step": 4090}, {"loss": 0.3404, "grad_norm": 0.9886922836303711, "learning_rate": 0.0002, "epoch": 5.036855036855036, "step": 4100}, {"loss": 0.3529, "grad_norm": 0.7880306243896484, "learning_rate": 0.0002, "epoch": 5.049140049140049, "step": 4110}, {"loss": 0.3406, "grad_norm": 0.7488741874694824, "learning_rate": 0.0002, "epoch": 5.061425061425061, "step": 4120}, {"loss": 0.3542, "grad_norm": 0.9359086751937866, "learning_rate": 0.0002, "epoch": 5.073710073710074, "step": 4130}, {"loss": 0.3471, "grad_norm": 0.9401527047157288, "learning_rate": 0.0002, "epoch": 5.085995085995086, "step": 4140}, {"loss": 0.3566, "grad_norm": 0.8396275043487549, "learning_rate": 0.0002, "epoch": 5.098280098280099, "step": 4150}, {"loss": 0.3416, "grad_norm": 0.7132664918899536, "learning_rate": 0.0002, "epoch": 5.11056511056511, "step": 4160}, {"loss": 0.3457, "grad_norm": 0.843708872795105, "learning_rate": 0.0002, "epoch": 5.122850122850123, "step": 4170}, {"loss": 0.3399, "grad_norm": 0.8733304738998413, "learning_rate": 0.0002, "epoch": 5.135135135135135, "step": 4180}, {"loss": 0.3501, "grad_norm": 0.9064375162124634, "learning_rate": 0.0002, "epoch": 5.1474201474201475, "step": 4190}, {"loss": 0.3455, "grad_norm": 0.900770902633667, "learning_rate": 0.0002, "epoch": 5.15970515970516, "step": 4200}, {"loss": 0.3475, "grad_norm": 0.863853394985199, "learning_rate": 0.0002, "epoch": 5.171990171990172, "step": 4210}, {"loss": 0.3497, "grad_norm": 0.767134964466095, "learning_rate": 0.0002, "epoch": 5.184275184275184, "step": 4220}, {"loss": 0.3527, "grad_norm": 0.7518735527992249, "learning_rate": 0.0002, "epoch": 5.196560196560196, "step": 4230}, {"loss": 0.3369, "grad_norm": 0.8040947914123535, "learning_rate": 0.0002, "epoch": 5.208845208845209, "step": 4240}, {"loss": 0.3496, "grad_norm": 0.7827144265174866, "learning_rate": 0.0002, "epoch": 5.221130221130221, "step": 4250}, {"loss": 0.3442, "grad_norm": 0.7306333184242249, "learning_rate": 0.0002, "epoch": 5.233415233415234, "step": 4260}, {"loss": 0.3553, "grad_norm": 1.0963380336761475, "learning_rate": 0.0002, "epoch": 5.245700245700245, "step": 4270}, {"loss": 0.3462, "grad_norm": 0.8200454711914062, "learning_rate": 0.0002, "epoch": 5.257985257985258, "step": 4280}, {"loss": 0.3509, "grad_norm": 0.8666796684265137, "learning_rate": 0.0002, "epoch": 5.27027027027027, "step": 4290}, {"loss": 0.3423, "grad_norm": 0.7862894535064697, "learning_rate": 0.0002, "epoch": 5.282555282555283, "step": 4300}, {"loss": 0.3623, "grad_norm": 0.8163095712661743, "learning_rate": 0.0002, "epoch": 5.294840294840295, "step": 4310}, {"loss": 0.34, "grad_norm": 0.8069050908088684, "learning_rate": 0.0002, "epoch": 5.3071253071253075, "step": 4320}, {"loss": 0.3532, "grad_norm": 0.7858486175537109, "learning_rate": 0.0002, "epoch": 5.319410319410319, "step": 4330}, {"loss": 0.3435, "grad_norm": 0.950339674949646, "learning_rate": 0.0002, "epoch": 5.3316953316953315, "step": 4340}, {"loss": 0.3498, "grad_norm": 0.9056477546691895, "learning_rate": 0.0002, "epoch": 5.343980343980344, "step": 4350}, {"loss": 0.3538, "grad_norm": 0.9619399905204773, "learning_rate": 0.0002, "epoch": 5.356265356265356, "step": 4360}, {"loss": 0.3455, "grad_norm": 0.9778652191162109, "learning_rate": 0.0002, "epoch": 5.368550368550369, "step": 4370}, {"loss": 0.3498, "grad_norm": 0.6919555068016052, "learning_rate": 0.0002, "epoch": 5.38083538083538, "step": 4380}, {"loss": 0.3426, "grad_norm": 0.8121668696403503, "learning_rate": 0.0002, "epoch": 5.393120393120393, "step": 4390}, {"loss": 0.3442, "grad_norm": 0.8481289148330688, "learning_rate": 0.0002, "epoch": 5.405405405405405, "step": 4400}, {"loss": 0.345, "grad_norm": 0.8727408647537231, "learning_rate": 0.0002, "epoch": 5.417690417690418, "step": 4410}, {"loss": 0.3554, "grad_norm": 0.8920271396636963, "learning_rate": 0.0002, "epoch": 5.42997542997543, "step": 4420}, {"loss": 0.3409, "grad_norm": 0.7758749723434448, "learning_rate": 0.0002, "epoch": 5.442260442260443, "step": 4430}, {"loss": 0.3483, "grad_norm": 0.8847506642341614, "learning_rate": 0.0002, "epoch": 5.454545454545454, "step": 4440}, {"loss": 0.3557, "grad_norm": 0.9760470390319824, "learning_rate": 0.0002, "epoch": 5.466830466830467, "step": 4450}, {"loss": 0.3536, "grad_norm": 0.8940271139144897, "learning_rate": 0.0002, "epoch": 5.479115479115479, "step": 4460}, {"loss": 0.3577, "grad_norm": 0.8668502569198608, "learning_rate": 0.0002, "epoch": 5.4914004914004915, "step": 4470}, {"loss": 0.3462, "grad_norm": 0.9097439050674438, "learning_rate": 0.0002, "epoch": 5.503685503685504, "step": 4480}, {"loss": 0.3417, "grad_norm": 0.8217208981513977, "learning_rate": 0.0002, "epoch": 5.515970515970516, "step": 4490}, {"loss": 0.3482, "grad_norm": 0.7853189706802368, "learning_rate": 0.0002, "epoch": 5.528255528255528, "step": 4500}, {"loss": 0.3479, "grad_norm": 1.1113477945327759, "learning_rate": 0.0002, "epoch": 5.54054054054054, "step": 4510}, {"loss": 0.3553, "grad_norm": 0.8637538552284241, "learning_rate": 0.0002, "epoch": 5.552825552825553, "step": 4520}, {"loss": 0.3403, "grad_norm": 1.0230066776275635, "learning_rate": 0.0002, "epoch": 5.565110565110565, "step": 4530}, {"loss": 0.3588, "grad_norm": 0.8972793817520142, "learning_rate": 0.0002, "epoch": 5.577395577395578, "step": 4540}, {"loss": 0.3428, "grad_norm": 0.7950642704963684, "learning_rate": 0.0002, "epoch": 5.58968058968059, "step": 4550}, {"loss": 0.3468, "grad_norm": 1.113753318786621, "learning_rate": 0.0002, "epoch": 5.601965601965602, "step": 4560}, {"loss": 0.3354, "grad_norm": 0.7842669486999512, "learning_rate": 0.0002, "epoch": 5.614250614250614, "step": 4570}, {"loss": 0.3419, "grad_norm": 0.9713512063026428, "learning_rate": 0.0002, "epoch": 5.6265356265356266, "step": 4580}, {"loss": 0.3502, "grad_norm": 0.9451650977134705, "learning_rate": 0.0002, "epoch": 5.638820638820639, "step": 4590}, {"loss": 0.3416, "grad_norm": 1.055484414100647, "learning_rate": 0.0002, "epoch": 5.651105651105651, "step": 4600}, {"loss": 0.3436, "grad_norm": 0.8408507704734802, "learning_rate": 0.0002, "epoch": 5.663390663390663, "step": 4610}, {"loss": 0.3619, "grad_norm": 1.0293926000595093, "learning_rate": 0.0002, "epoch": 5.675675675675675, "step": 4620}, {"loss": 0.3484, "grad_norm": 0.7198245525360107, "learning_rate": 0.0002, "epoch": 5.687960687960688, "step": 4630}, {"loss": 0.3563, "grad_norm": 0.7564466595649719, "learning_rate": 0.0002, "epoch": 5.7002457002457, "step": 4640}, {"loss": 0.3435, "grad_norm": 0.7980002760887146, "learning_rate": 0.0002, "epoch": 5.712530712530713, "step": 4650}, {"loss": 0.3478, "grad_norm": 0.8685088753700256, "learning_rate": 0.0002, "epoch": 5.724815724815725, "step": 4660}, {"loss": 0.3692, "grad_norm": 0.8816949129104614, "learning_rate": 0.0002, "epoch": 5.737100737100737, "step": 4670}, {"loss": 0.3462, "grad_norm": 0.7154731750488281, "learning_rate": 0.0002, "epoch": 5.749385749385749, "step": 4680}, {"loss": 0.3503, "grad_norm": 0.9430679678916931, "learning_rate": 0.0002, "epoch": 5.761670761670762, "step": 4690}, {"loss": 0.3439, "grad_norm": 0.7640151381492615, "learning_rate": 0.0002, "epoch": 5.773955773955774, "step": 4700}, {"loss": 0.3444, "grad_norm": 1.0920690298080444, "learning_rate": 0.0002, "epoch": 5.7862407862407865, "step": 4710}, {"loss": 0.3356, "grad_norm": 0.9362104535102844, "learning_rate": 0.0002, "epoch": 5.798525798525798, "step": 4720}, {"loss": 0.339, "grad_norm": 0.8392294645309448, "learning_rate": 0.0002, "epoch": 5.8108108108108105, "step": 4730}, {"loss": 0.3488, "grad_norm": 0.9893582463264465, "learning_rate": 0.0002, "epoch": 5.823095823095823, "step": 4740}, {"loss": 0.3446, "grad_norm": 0.6985510587692261, "learning_rate": 0.0002, "epoch": 5.835380835380835, "step": 4750}, {"loss": 0.3534, "grad_norm": 0.8906862735748291, "learning_rate": 0.0002, "epoch": 5.847665847665848, "step": 4760}, {"loss": 0.3481, "grad_norm": 0.8036413192749023, "learning_rate": 0.0002, "epoch": 5.85995085995086, "step": 4770}, {"loss": 0.3326, "grad_norm": 0.9948155283927917, "learning_rate": 0.0002, "epoch": 5.872235872235873, "step": 4780}, {"loss": 0.3385, "grad_norm": 0.8618432283401489, "learning_rate": 0.0002, "epoch": 5.884520884520884, "step": 4790}, {"loss": 0.3302, "grad_norm": 1.0422909259796143, "learning_rate": 0.0002, "epoch": 5.896805896805897, "step": 4800}, {"loss": 0.3448, "grad_norm": 1.1892569065093994, "learning_rate": 0.0002, "epoch": 5.909090909090909, "step": 4810}, {"loss": 0.3506, "grad_norm": 1.1459916830062866, "learning_rate": 0.0002, "epoch": 5.921375921375922, "step": 4820}, {"loss": 0.3387, "grad_norm": 1.056235909461975, "learning_rate": 0.0002, "epoch": 5.933660933660933, "step": 4830}, {"loss": 0.344, "grad_norm": 0.8517277240753174, "learning_rate": 0.0002, "epoch": 5.945945945945946, "step": 4840}, {"loss": 0.3421, "grad_norm": 0.8153380751609802, "learning_rate": 0.0002, "epoch": 5.958230958230958, "step": 4850}, {"loss": 0.3409, "grad_norm": 0.7907533049583435, "learning_rate": 0.0002, "epoch": 5.9705159705159705, "step": 4860}, {"loss": 0.3337, "grad_norm": 0.8443069458007812, "learning_rate": 0.0002, "epoch": 5.982800982800983, "step": 4870}, {"loss": 0.3351, "grad_norm": 0.8711344003677368, "learning_rate": 0.0002, "epoch": 5.995085995085995, "step": 4880}]}
+{"epoch": 7.0, "step": 5698, "epoch_duration": 779.5834319591522, "total_accumulated_duration": 5272.349390506744, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-4884", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}, {"eval_loss": 0.49752503633499146, "eval_runtime": 20.2911, "eval_samples_per_second": 16.313, "eval_steps_per_second": 2.07, "epoch": 3.0, "step": 2442}, {"loss": 0.4362, "grad_norm": 0.7644656896591187, "learning_rate": 0.0002, "epoch": 3.0098280098280097, "step": 2450}, {"loss": 0.4363, "grad_norm": 0.9077525734901428, "learning_rate": 0.0002, "epoch": 3.022113022113022, "step": 2460}, {"loss": 0.422, "grad_norm": 0.7859287261962891, "learning_rate": 0.0002, "epoch": 3.0343980343980346, "step": 2470}, {"loss": 0.4574, "grad_norm": 1.1200323104858398, "learning_rate": 0.0002, "epoch": 3.0466830466830466, "step": 2480}, {"loss": 0.4519, "grad_norm": 0.7570453882217407, "learning_rate": 0.0002, "epoch": 3.058968058968059, "step": 2490}, {"loss": 0.4351, "grad_norm": 0.9450915455818176, "learning_rate": 0.0002, "epoch": 3.0712530712530715, "step": 2500}, {"loss": 0.4343, "grad_norm": 0.8303545117378235, "learning_rate": 0.0002, "epoch": 3.0835380835380835, "step": 2510}, {"loss": 0.4308, "grad_norm": 0.8864443898200989, "learning_rate": 0.0002, "epoch": 3.095823095823096, "step": 2520}, {"loss": 0.4601, "grad_norm": 0.945324718952179, "learning_rate": 0.0002, "epoch": 3.108108108108108, "step": 2530}, {"loss": 0.4345, "grad_norm": 1.0562494993209839, "learning_rate": 0.0002, "epoch": 3.1203931203931203, "step": 2540}, {"loss": 0.4375, "grad_norm": 0.8607500195503235, "learning_rate": 0.0002, "epoch": 3.1326781326781328, "step": 2550}, {"loss": 0.456, "grad_norm": 0.8719640374183655, "learning_rate": 0.0002, "epoch": 3.1449631449631448, "step": 2560}, {"loss": 0.4469, "grad_norm": 0.8647059202194214, "learning_rate": 0.0002, "epoch": 3.157248157248157, "step": 2570}, {"loss": 0.4483, "grad_norm": 0.8346507549285889, "learning_rate": 0.0002, "epoch": 3.1695331695331697, "step": 2580}, {"loss": 0.4331, "grad_norm": 1.0208854675292969, "learning_rate": 0.0002, "epoch": 3.1818181818181817, "step": 2590}, {"loss": 0.435, "grad_norm": 0.7064385414123535, "learning_rate": 0.0002, "epoch": 3.194103194103194, "step": 2600}, {"loss": 0.4541, "grad_norm": 0.927347719669342, "learning_rate": 0.0002, "epoch": 3.2063882063882065, "step": 2610}, {"loss": 0.4561, "grad_norm": 0.943517804145813, "learning_rate": 0.0002, "epoch": 3.2186732186732185, "step": 2620}, {"loss": 0.4225, "grad_norm": 0.7837198376655579, "learning_rate": 0.0002, "epoch": 3.230958230958231, "step": 2630}, {"loss": 0.4494, "grad_norm": 0.7752765417098999, "learning_rate": 0.0002, "epoch": 3.2432432432432434, "step": 2640}, {"loss": 0.4468, "grad_norm": 0.8578953146934509, "learning_rate": 0.0002, "epoch": 3.2555282555282554, "step": 2650}, {"loss": 0.4393, "grad_norm": 1.0209529399871826, "learning_rate": 0.0002, "epoch": 3.267813267813268, "step": 2660}, {"loss": 0.4517, "grad_norm": 0.9069030284881592, "learning_rate": 0.0002, "epoch": 3.2800982800982803, "step": 2670}, {"loss": 0.4262, "grad_norm": 0.8454729318618774, "learning_rate": 0.0002, "epoch": 3.2923832923832923, "step": 2680}, {"loss": 0.4349, "grad_norm": 0.8253099322319031, "learning_rate": 0.0002, "epoch": 3.3046683046683047, "step": 2690}, {"loss": 0.4503, "grad_norm": 0.8765934109687805, "learning_rate": 0.0002, "epoch": 3.3169533169533167, "step": 2700}, {"loss": 0.4518, "grad_norm": 0.8149126172065735, "learning_rate": 0.0002, "epoch": 3.329238329238329, "step": 2710}, {"loss": 0.4437, "grad_norm": 0.8820102214813232, "learning_rate": 0.0002, "epoch": 3.3415233415233416, "step": 2720}, {"loss": 0.4346, "grad_norm": 0.8813952803611755, "learning_rate": 0.0002, "epoch": 3.3538083538083536, "step": 2730}, {"loss": 0.4396, "grad_norm": 1.0338447093963623, "learning_rate": 0.0002, "epoch": 3.366093366093366, "step": 2740}, {"loss": 0.4468, "grad_norm": 0.8780209422111511, "learning_rate": 0.0002, "epoch": 3.3783783783783785, "step": 2750}, {"loss": 0.441, "grad_norm": 0.9017151594161987, "learning_rate": 0.0002, "epoch": 3.3906633906633905, "step": 2760}, {"loss": 0.446, "grad_norm": 0.8647638559341431, "learning_rate": 0.0002, "epoch": 3.402948402948403, "step": 2770}, {"loss": 0.4131, "grad_norm": 0.8298183679580688, "learning_rate": 0.0002, "epoch": 3.4152334152334154, "step": 2780}, {"loss": 0.4406, "grad_norm": 0.9298108816146851, "learning_rate": 0.0002, "epoch": 3.4275184275184274, "step": 2790}, {"loss": 0.4145, "grad_norm": 0.8909980058670044, "learning_rate": 0.0002, "epoch": 3.43980343980344, "step": 2800}, {"loss": 0.4148, "grad_norm": 0.8027496933937073, "learning_rate": 0.0002, "epoch": 3.4520884520884523, "step": 2810}, {"loss": 0.4244, "grad_norm": 0.8766195774078369, "learning_rate": 0.0002, "epoch": 3.4643734643734643, "step": 2820}, {"loss": 0.4292, "grad_norm": 0.8194443583488464, "learning_rate": 0.0002, "epoch": 3.4766584766584767, "step": 2830}, {"loss": 0.4305, "grad_norm": 0.9862873554229736, "learning_rate": 0.0002, "epoch": 3.488943488943489, "step": 2840}, {"loss": 0.4393, "grad_norm": 0.8755377531051636, "learning_rate": 0.0002, "epoch": 3.501228501228501, "step": 2850}, {"loss": 0.4231, "grad_norm": 0.7300266027450562, "learning_rate": 0.0002, "epoch": 3.5135135135135136, "step": 2860}, {"loss": 0.4278, "grad_norm": 0.8342461585998535, "learning_rate": 0.0002, "epoch": 3.5257985257985256, "step": 2870}, {"loss": 0.4395, "grad_norm": 0.8624151349067688, "learning_rate": 0.0002, "epoch": 3.538083538083538, "step": 2880}, {"loss": 0.4064, "grad_norm": 0.8931261301040649, "learning_rate": 0.0002, "epoch": 3.5503685503685505, "step": 2890}, {"loss": 0.4358, "grad_norm": 0.8617086410522461, "learning_rate": 0.0002, "epoch": 3.562653562653563, "step": 2900}, {"loss": 0.419, "grad_norm": 0.8754099607467651, "learning_rate": 0.0002, "epoch": 3.574938574938575, "step": 2910}, {"loss": 0.4275, "grad_norm": 0.8345834612846375, "learning_rate": 0.0002, "epoch": 3.5872235872235874, "step": 2920}, {"loss": 0.4375, "grad_norm": 1.1414062976837158, "learning_rate": 0.0002, "epoch": 3.5995085995085994, "step": 2930}, {"loss": 0.4297, "grad_norm": 0.994860053062439, "learning_rate": 0.0002, "epoch": 3.611793611793612, "step": 2940}, {"loss": 0.4386, "grad_norm": 1.19268000125885, "learning_rate": 0.0002, "epoch": 3.6240786240786242, "step": 2950}, {"loss": 0.4029, "grad_norm": 0.8399543762207031, "learning_rate": 0.0002, "epoch": 3.6363636363636362, "step": 2960}, {"loss": 0.4432, "grad_norm": 0.9873217940330505, "learning_rate": 0.0002, "epoch": 3.6486486486486487, "step": 2970}, {"loss": 0.4308, "grad_norm": 0.9116013646125793, "learning_rate": 0.0002, "epoch": 3.6609336609336607, "step": 2980}, {"loss": 0.4275, "grad_norm": 0.9503833651542664, "learning_rate": 0.0002, "epoch": 3.673218673218673, "step": 2990}, {"loss": 0.4306, "grad_norm": 0.9401112794876099, "learning_rate": 0.0002, "epoch": 3.6855036855036856, "step": 3000}, {"loss": 0.4333, "grad_norm": 1.00745689868927, "learning_rate": 0.0002, "epoch": 3.697788697788698, "step": 3010}, {"loss": 0.432, "grad_norm": 1.0553191900253296, "learning_rate": 0.0002, "epoch": 3.71007371007371, "step": 3020}, {"loss": 0.4321, "grad_norm": 1.0226953029632568, "learning_rate": 0.0002, "epoch": 3.7223587223587224, "step": 3030}, {"loss": 0.418, "grad_norm": 1.085554838180542, "learning_rate": 0.0002, "epoch": 3.7346437346437344, "step": 3040}, {"loss": 0.4196, "grad_norm": 0.9948731064796448, "learning_rate": 0.0002, "epoch": 3.746928746928747, "step": 3050}, {"loss": 0.4281, "grad_norm": 0.9328727126121521, "learning_rate": 0.0002, "epoch": 3.7592137592137593, "step": 3060}, {"loss": 0.4284, "grad_norm": 1.0533266067504883, "learning_rate": 0.0002, "epoch": 3.7714987714987718, "step": 3070}, {"loss": 0.4414, "grad_norm": 0.8213809132575989, "learning_rate": 0.0002, "epoch": 3.7837837837837838, "step": 3080}, {"loss": 0.4348, "grad_norm": 0.8941594362258911, "learning_rate": 0.0002, "epoch": 3.796068796068796, "step": 3090}, {"loss": 0.4266, "grad_norm": 0.8324518203735352, "learning_rate": 0.0002, "epoch": 3.808353808353808, "step": 3100}, {"loss": 0.4227, "grad_norm": 0.8811233639717102, "learning_rate": 0.0002, "epoch": 3.8206388206388207, "step": 3110}, {"loss": 0.4195, "grad_norm": 0.8781470060348511, "learning_rate": 0.0002, "epoch": 3.832923832923833, "step": 3120}, {"loss": 0.4277, "grad_norm": 0.8994116187095642, "learning_rate": 0.0002, "epoch": 3.845208845208845, "step": 3130}, {"loss": 0.4149, "grad_norm": 0.8605017066001892, "learning_rate": 0.0002, "epoch": 3.8574938574938575, "step": 3140}, {"loss": 0.4023, "grad_norm": 0.8966400027275085, "learning_rate": 0.0002, "epoch": 3.8697788697788695, "step": 3150}, {"loss": 0.4245, "grad_norm": 0.8856554627418518, "learning_rate": 0.0002, "epoch": 3.882063882063882, "step": 3160}, {"loss": 0.4101, "grad_norm": 0.8971620798110962, "learning_rate": 0.0002, "epoch": 3.8943488943488944, "step": 3170}, {"loss": 0.3993, "grad_norm": 0.9807813167572021, "learning_rate": 0.0002, "epoch": 3.906633906633907, "step": 3180}, {"loss": 0.4258, "grad_norm": 0.8614121675491333, "learning_rate": 0.0002, "epoch": 3.918918918918919, "step": 3190}, {"loss": 0.4115, "grad_norm": 0.989171028137207, "learning_rate": 0.0002, "epoch": 3.9312039312039313, "step": 3200}, {"loss": 0.4182, "grad_norm": 0.8168872594833374, "learning_rate": 0.0002, "epoch": 3.9434889434889433, "step": 3210}, {"loss": 0.4112, "grad_norm": 0.8109386563301086, "learning_rate": 0.0002, "epoch": 3.9557739557739557, "step": 3220}, {"loss": 0.4165, "grad_norm": 1.0175853967666626, "learning_rate": 0.0002, "epoch": 3.968058968058968, "step": 3230}, {"loss": 0.4146, "grad_norm": 0.936143159866333, "learning_rate": 0.0002, "epoch": 3.98034398034398, "step": 3240}, {"loss": 0.4163, "grad_norm": 0.9557915925979614, "learning_rate": 0.0002, "epoch": 3.9926289926289926, "step": 3250}, {"eval_loss": 0.4401616156101227, "eval_runtime": 20.8047, "eval_samples_per_second": 15.91, "eval_steps_per_second": 2.019, "epoch": 4.0, "step": 3256}, {"loss": 0.408, "grad_norm": 0.7590614557266235, "learning_rate": 0.0002, "epoch": 4.004914004914005, "step": 3260}, {"loss": 0.4001, "grad_norm": 0.8920791149139404, "learning_rate": 0.0002, "epoch": 4.017199017199017, "step": 3270}, {"loss": 0.3789, "grad_norm": 0.8640421628952026, "learning_rate": 0.0002, "epoch": 4.0294840294840295, "step": 3280}, {"loss": 0.3791, "grad_norm": 0.9074113965034485, "learning_rate": 0.0002, "epoch": 4.041769041769042, "step": 3290}, {"loss": 0.3728, "grad_norm": 1.0600885152816772, "learning_rate": 0.0002, "epoch": 4.054054054054054, "step": 3300}, {"loss": 0.3857, "grad_norm": 0.9682773351669312, "learning_rate": 0.0002, "epoch": 4.066339066339066, "step": 3310}, {"loss": 0.4007, "grad_norm": 0.9326395392417908, "learning_rate": 0.0002, "epoch": 4.078624078624078, "step": 3320}, {"loss": 0.3823, "grad_norm": 0.8886597156524658, "learning_rate": 0.0002, "epoch": 4.090909090909091, "step": 3330}, {"loss": 0.3929, "grad_norm": 1.032205581665039, "learning_rate": 0.0002, "epoch": 4.103194103194103, "step": 3340}, {"loss": 0.3836, "grad_norm": 0.8669408559799194, "learning_rate": 0.0002, "epoch": 4.115479115479116, "step": 3350}, {"loss": 0.3866, "grad_norm": 0.8250347971916199, "learning_rate": 0.0002, "epoch": 4.127764127764128, "step": 3360}, {"loss": 0.3826, "grad_norm": 0.7919842600822449, "learning_rate": 0.0002, "epoch": 4.14004914004914, "step": 3370}, {"loss": 0.3838, "grad_norm": 1.045682430267334, "learning_rate": 0.0002, "epoch": 4.152334152334152, "step": 3380}, {"loss": 0.3796, "grad_norm": 0.6873571276664734, "learning_rate": 0.0002, "epoch": 4.164619164619165, "step": 3390}, {"loss": 0.3942, "grad_norm": 1.0227675437927246, "learning_rate": 0.0002, "epoch": 4.176904176904177, "step": 3400}, {"loss": 0.3788, "grad_norm": 0.9167711734771729, "learning_rate": 0.0002, "epoch": 4.1891891891891895, "step": 3410}, {"loss": 0.3792, "grad_norm": 1.0598796606063843, "learning_rate": 0.0002, "epoch": 4.201474201474202, "step": 3420}, {"loss": 0.3955, "grad_norm": 0.8581843972206116, "learning_rate": 0.0002, "epoch": 4.2137592137592135, "step": 3430}, {"loss": 0.3761, "grad_norm": 0.8862360119819641, "learning_rate": 0.0002, "epoch": 4.226044226044226, "step": 3440}, {"loss": 0.3889, "grad_norm": 1.0248323678970337, "learning_rate": 0.0002, "epoch": 4.238329238329238, "step": 3450}, {"loss": 0.3827, "grad_norm": 0.8746261596679688, "learning_rate": 0.0002, "epoch": 4.250614250614251, "step": 3460}, {"loss": 0.3949, "grad_norm": 0.7442536354064941, "learning_rate": 0.0002, "epoch": 4.262899262899263, "step": 3470}, {"loss": 0.3761, "grad_norm": 0.8295119404792786, "learning_rate": 0.0002, "epoch": 4.275184275184275, "step": 3480}, {"loss": 0.3895, "grad_norm": 1.0634245872497559, "learning_rate": 0.0002, "epoch": 4.287469287469287, "step": 3490}, {"loss": 0.3955, "grad_norm": 0.9554621577262878, "learning_rate": 0.0002, "epoch": 4.2997542997543, "step": 3500}, {"loss": 0.3826, "grad_norm": 1.0191723108291626, "learning_rate": 0.0002, "epoch": 4.312039312039312, "step": 3510}, {"loss": 0.3828, "grad_norm": 0.8573611378669739, "learning_rate": 0.0002, "epoch": 4.324324324324325, "step": 3520}, {"loss": 0.3869, "grad_norm": 0.9082390069961548, "learning_rate": 0.0002, "epoch": 4.336609336609337, "step": 3530}, {"loss": 0.3902, "grad_norm": 0.8650212287902832, "learning_rate": 0.0002, "epoch": 4.348894348894349, "step": 3540}, {"loss": 0.3915, "grad_norm": 0.7186297178268433, "learning_rate": 0.0002, "epoch": 4.361179361179361, "step": 3550}, {"loss": 0.3861, "grad_norm": 0.9750986695289612, "learning_rate": 0.0002, "epoch": 4.3734643734643734, "step": 3560}, {"loss": 0.3967, "grad_norm": 1.0710467100143433, "learning_rate": 0.0002, "epoch": 4.385749385749386, "step": 3570}, {"loss": 0.3774, "grad_norm": 0.7974869012832642, "learning_rate": 0.0002, "epoch": 4.398034398034398, "step": 3580}, {"loss": 0.3738, "grad_norm": 0.9405913949012756, "learning_rate": 0.0002, "epoch": 4.41031941031941, "step": 3590}, {"loss": 0.3982, "grad_norm": 0.9393602609634399, "learning_rate": 0.0002, "epoch": 4.422604422604422, "step": 3600}, {"loss": 0.3913, "grad_norm": 1.0798007249832153, "learning_rate": 0.0002, "epoch": 4.434889434889435, "step": 3610}, {"loss": 0.3682, "grad_norm": 0.9226186275482178, "learning_rate": 0.0002, "epoch": 4.447174447174447, "step": 3620}, {"loss": 0.3742, "grad_norm": 1.1046524047851562, "learning_rate": 0.0002, "epoch": 4.45945945945946, "step": 3630}, {"loss": 0.3886, "grad_norm": 0.8848567605018616, "learning_rate": 0.0002, "epoch": 4.471744471744472, "step": 3640}, {"loss": 0.3848, "grad_norm": 0.8913224339485168, "learning_rate": 0.0002, "epoch": 4.484029484029484, "step": 3650}, {"loss": 0.3731, "grad_norm": 0.8497583270072937, "learning_rate": 0.0002, "epoch": 4.496314496314496, "step": 3660}, {"loss": 0.3804, "grad_norm": 0.8263831734657288, "learning_rate": 0.0002, "epoch": 4.5085995085995085, "step": 3670}, {"loss": 0.3815, "grad_norm": 0.8470269441604614, "learning_rate": 0.0002, "epoch": 4.520884520884521, "step": 3680}, {"loss": 0.3774, "grad_norm": 0.860038161277771, "learning_rate": 0.0002, "epoch": 4.533169533169533, "step": 3690}, {"loss": 0.3817, "grad_norm": 0.8898552656173706, "learning_rate": 0.0002, "epoch": 4.545454545454545, "step": 3700}, {"loss": 0.3776, "grad_norm": 0.8152070641517639, "learning_rate": 0.0002, "epoch": 4.557739557739557, "step": 3710}, {"loss": 0.383, "grad_norm": 0.7847675085067749, "learning_rate": 0.0002, "epoch": 4.57002457002457, "step": 3720}, {"loss": 0.3791, "grad_norm": 0.9625533819198608, "learning_rate": 0.0002, "epoch": 4.582309582309582, "step": 3730}, {"loss": 0.3699, "grad_norm": 0.9097456336021423, "learning_rate": 0.0002, "epoch": 4.594594594594595, "step": 3740}, {"loss": 0.3673, "grad_norm": 0.871329128742218, "learning_rate": 0.0002, "epoch": 4.606879606879607, "step": 3750}, {"loss": 0.3725, "grad_norm": 0.9879975914955139, "learning_rate": 0.0002, "epoch": 4.61916461916462, "step": 3760}, {"loss": 0.3827, "grad_norm": 0.8636731505393982, "learning_rate": 0.0002, "epoch": 4.631449631449631, "step": 3770}, {"loss": 0.3755, "grad_norm": 1.0488964319229126, "learning_rate": 0.0002, "epoch": 4.643734643734644, "step": 3780}, {"loss": 0.3738, "grad_norm": 0.7637056112289429, "learning_rate": 0.0002, "epoch": 4.656019656019656, "step": 3790}, {"loss": 0.3676, "grad_norm": 0.8507546186447144, "learning_rate": 0.0002, "epoch": 4.6683046683046685, "step": 3800}, {"loss": 0.3852, "grad_norm": 1.0216856002807617, "learning_rate": 0.0002, "epoch": 4.680589680589681, "step": 3810}, {"loss": 0.3751, "grad_norm": 1.026343822479248, "learning_rate": 0.0002, "epoch": 4.6928746928746925, "step": 3820}, {"loss": 0.3687, "grad_norm": 0.8311620950698853, "learning_rate": 0.0002, "epoch": 4.705159705159705, "step": 3830}, {"loss": 0.3771, "grad_norm": 0.7770653367042542, "learning_rate": 0.0002, "epoch": 4.717444717444717, "step": 3840}, {"loss": 0.37, "grad_norm": 0.7616215348243713, "learning_rate": 0.0002, "epoch": 4.72972972972973, "step": 3850}, {"loss": 0.3927, "grad_norm": 1.0377072095870972, "learning_rate": 0.0002, "epoch": 4.742014742014742, "step": 3860}, {"loss": 0.3832, "grad_norm": 0.9713505506515503, "learning_rate": 0.0002, "epoch": 4.754299754299755, "step": 3870}, {"loss": 0.3722, "grad_norm": 0.8803321719169617, "learning_rate": 0.0002, "epoch": 4.766584766584766, "step": 3880}, {"loss": 0.3756, "grad_norm": 0.885535478591919, "learning_rate": 0.0002, "epoch": 4.778869778869779, "step": 3890}, {"loss": 0.3714, "grad_norm": 1.0877983570098877, "learning_rate": 0.0002, "epoch": 4.791154791154791, "step": 3900}, {"loss": 0.3879, "grad_norm": 0.7875366806983948, "learning_rate": 0.0002, "epoch": 4.803439803439804, "step": 3910}, {"loss": 0.3591, "grad_norm": 0.8550102114677429, "learning_rate": 0.0002, "epoch": 4.815724815724816, "step": 3920}, {"loss": 0.3716, "grad_norm": 1.0217846632003784, "learning_rate": 0.0002, "epoch": 4.828009828009828, "step": 3930}, {"loss": 0.3649, "grad_norm": 0.7315713167190552, "learning_rate": 0.0002, "epoch": 4.84029484029484, "step": 3940}, {"loss": 0.3879, "grad_norm": 0.8924923539161682, "learning_rate": 0.0002, "epoch": 4.8525798525798525, "step": 3950}, {"loss": 0.3669, "grad_norm": 0.9730218052864075, "learning_rate": 0.0002, "epoch": 4.864864864864865, "step": 3960}, {"loss": 0.3705, "grad_norm": 0.9202003479003906, "learning_rate": 0.0002, "epoch": 4.877149877149877, "step": 3970}, {"loss": 0.3617, "grad_norm": 0.8173081874847412, "learning_rate": 0.0002, "epoch": 4.88943488943489, "step": 3980}, {"loss": 0.37, "grad_norm": 0.7178564667701721, "learning_rate": 0.0002, "epoch": 4.901719901719901, "step": 3990}, {"loss": 0.3768, "grad_norm": 0.913684606552124, "learning_rate": 0.0002, "epoch": 4.914004914004914, "step": 4000}, {"loss": 0.3755, "grad_norm": 0.8817896842956543, "learning_rate": 0.0002, "epoch": 4.926289926289926, "step": 4010}, {"loss": 0.3676, "grad_norm": 0.7652186751365662, "learning_rate": 0.0002, "epoch": 4.938574938574939, "step": 4020}, {"loss": 0.3699, "grad_norm": 0.8828630447387695, "learning_rate": 0.0002, "epoch": 4.950859950859951, "step": 4030}, {"loss": 0.3672, "grad_norm": 1.0878605842590332, "learning_rate": 0.0002, "epoch": 4.963144963144963, "step": 4040}, {"loss": 0.3656, "grad_norm": 1.0845288038253784, "learning_rate": 0.0002, "epoch": 4.975429975429975, "step": 4050}, {"loss": 0.365, "grad_norm": 0.8431115746498108, "learning_rate": 0.0002, "epoch": 4.987714987714988, "step": 4060}, {"loss": 0.3693, "grad_norm": 0.8320387601852417, "learning_rate": 0.0002, "epoch": 5.0, "step": 4070}, {"eval_loss": 0.4017423093318939, "eval_runtime": 20.8466, "eval_samples_per_second": 15.878, "eval_steps_per_second": 2.015, "epoch": 5.0, "step": 4070}, {"loss": 0.3425, "grad_norm": 0.8639023900032043, "learning_rate": 0.0002, "epoch": 5.012285012285012, "step": 4080}, {"loss": 0.3458, "grad_norm": 0.7123713493347168, "learning_rate": 0.0002, "epoch": 5.024570024570025, "step": 4090}, {"loss": 0.3404, "grad_norm": 0.9886922836303711, "learning_rate": 0.0002, "epoch": 5.036855036855036, "step": 4100}, {"loss": 0.3529, "grad_norm": 0.7880306243896484, "learning_rate": 0.0002, "epoch": 5.049140049140049, "step": 4110}, {"loss": 0.3406, "grad_norm": 0.7488741874694824, "learning_rate": 0.0002, "epoch": 5.061425061425061, "step": 4120}, {"loss": 0.3542, "grad_norm": 0.9359086751937866, "learning_rate": 0.0002, "epoch": 5.073710073710074, "step": 4130}, {"loss": 0.3471, "grad_norm": 0.9401527047157288, "learning_rate": 0.0002, "epoch": 5.085995085995086, "step": 4140}, {"loss": 0.3566, "grad_norm": 0.8396275043487549, "learning_rate": 0.0002, "epoch": 5.098280098280099, "step": 4150}, {"loss": 0.3416, "grad_norm": 0.7132664918899536, "learning_rate": 0.0002, "epoch": 5.11056511056511, "step": 4160}, {"loss": 0.3457, "grad_norm": 0.843708872795105, "learning_rate": 0.0002, "epoch": 5.122850122850123, "step": 4170}, {"loss": 0.3399, "grad_norm": 0.8733304738998413, "learning_rate": 0.0002, "epoch": 5.135135135135135, "step": 4180}, {"loss": 0.3501, "grad_norm": 0.9064375162124634, "learning_rate": 0.0002, "epoch": 5.1474201474201475, "step": 4190}, {"loss": 0.3455, "grad_norm": 0.900770902633667, "learning_rate": 0.0002, "epoch": 5.15970515970516, "step": 4200}, {"loss": 0.3475, "grad_norm": 0.863853394985199, "learning_rate": 0.0002, "epoch": 5.171990171990172, "step": 4210}, {"loss": 0.3497, "grad_norm": 0.767134964466095, "learning_rate": 0.0002, "epoch": 5.184275184275184, "step": 4220}, {"loss": 0.3527, "grad_norm": 0.7518735527992249, "learning_rate": 0.0002, "epoch": 5.196560196560196, "step": 4230}, {"loss": 0.3369, "grad_norm": 0.8040947914123535, "learning_rate": 0.0002, "epoch": 5.208845208845209, "step": 4240}, {"loss": 0.3496, "grad_norm": 0.7827144265174866, "learning_rate": 0.0002, "epoch": 5.221130221130221, "step": 4250}, {"loss": 0.3442, "grad_norm": 0.7306333184242249, "learning_rate": 0.0002, "epoch": 5.233415233415234, "step": 4260}, {"loss": 0.3553, "grad_norm": 1.0963380336761475, "learning_rate": 0.0002, "epoch": 5.245700245700245, "step": 4270}, {"loss": 0.3462, "grad_norm": 0.8200454711914062, "learning_rate": 0.0002, "epoch": 5.257985257985258, "step": 4280}, {"loss": 0.3509, "grad_norm": 0.8666796684265137, "learning_rate": 0.0002, "epoch": 5.27027027027027, "step": 4290}, {"loss": 0.3423, "grad_norm": 0.7862894535064697, "learning_rate": 0.0002, "epoch": 5.282555282555283, "step": 4300}, {"loss": 0.3623, "grad_norm": 0.8163095712661743, "learning_rate": 0.0002, "epoch": 5.294840294840295, "step": 4310}, {"loss": 0.34, "grad_norm": 0.8069050908088684, "learning_rate": 0.0002, "epoch": 5.3071253071253075, "step": 4320}, {"loss": 0.3532, "grad_norm": 0.7858486175537109, "learning_rate": 0.0002, "epoch": 5.319410319410319, "step": 4330}, {"loss": 0.3435, "grad_norm": 0.950339674949646, "learning_rate": 0.0002, "epoch": 5.3316953316953315, "step": 4340}, {"loss": 0.3498, "grad_norm": 0.9056477546691895, "learning_rate": 0.0002, "epoch": 5.343980343980344, "step": 4350}, {"loss": 0.3538, "grad_norm": 0.9619399905204773, "learning_rate": 0.0002, "epoch": 5.356265356265356, "step": 4360}, {"loss": 0.3455, "grad_norm": 0.9778652191162109, "learning_rate": 0.0002, "epoch": 5.368550368550369, "step": 4370}, {"loss": 0.3498, "grad_norm": 0.6919555068016052, "learning_rate": 0.0002, "epoch": 5.38083538083538, "step": 4380}, {"loss": 0.3426, "grad_norm": 0.8121668696403503, "learning_rate": 0.0002, "epoch": 5.393120393120393, "step": 4390}, {"loss": 0.3442, "grad_norm": 0.8481289148330688, "learning_rate": 0.0002, "epoch": 5.405405405405405, "step": 4400}, {"loss": 0.345, "grad_norm": 0.8727408647537231, "learning_rate": 0.0002, "epoch": 5.417690417690418, "step": 4410}, {"loss": 0.3554, "grad_norm": 0.8920271396636963, "learning_rate": 0.0002, "epoch": 5.42997542997543, "step": 4420}, {"loss": 0.3409, "grad_norm": 0.7758749723434448, "learning_rate": 0.0002, "epoch": 5.442260442260443, "step": 4430}, {"loss": 0.3483, "grad_norm": 0.8847506642341614, "learning_rate": 0.0002, "epoch": 5.454545454545454, "step": 4440}, {"loss": 0.3557, "grad_norm": 0.9760470390319824, "learning_rate": 0.0002, "epoch": 5.466830466830467, "step": 4450}, {"loss": 0.3536, "grad_norm": 0.8940271139144897, "learning_rate": 0.0002, "epoch": 5.479115479115479, "step": 4460}, {"loss": 0.3577, "grad_norm": 0.8668502569198608, "learning_rate": 0.0002, "epoch": 5.4914004914004915, "step": 4470}, {"loss": 0.3462, "grad_norm": 0.9097439050674438, "learning_rate": 0.0002, "epoch": 5.503685503685504, "step": 4480}, {"loss": 0.3417, "grad_norm": 0.8217208981513977, "learning_rate": 0.0002, "epoch": 5.515970515970516, "step": 4490}, {"loss": 0.3482, "grad_norm": 0.7853189706802368, "learning_rate": 0.0002, "epoch": 5.528255528255528, "step": 4500}, {"loss": 0.3479, "grad_norm": 1.1113477945327759, "learning_rate": 0.0002, "epoch": 5.54054054054054, "step": 4510}, {"loss": 0.3553, "grad_norm": 0.8637538552284241, "learning_rate": 0.0002, "epoch": 5.552825552825553, "step": 4520}, {"loss": 0.3403, "grad_norm": 1.0230066776275635, "learning_rate": 0.0002, "epoch": 5.565110565110565, "step": 4530}, {"loss": 0.3588, "grad_norm": 0.8972793817520142, "learning_rate": 0.0002, "epoch": 5.577395577395578, "step": 4540}, {"loss": 0.3428, "grad_norm": 0.7950642704963684, "learning_rate": 0.0002, "epoch": 5.58968058968059, "step": 4550}, {"loss": 0.3468, "grad_norm": 1.113753318786621, "learning_rate": 0.0002, "epoch": 5.601965601965602, "step": 4560}, {"loss": 0.3354, "grad_norm": 0.7842669486999512, "learning_rate": 0.0002, "epoch": 5.614250614250614, "step": 4570}, {"loss": 0.3419, "grad_norm": 0.9713512063026428, "learning_rate": 0.0002, "epoch": 5.6265356265356266, "step": 4580}, {"loss": 0.3502, "grad_norm": 0.9451650977134705, "learning_rate": 0.0002, "epoch": 5.638820638820639, "step": 4590}, {"loss": 0.3416, "grad_norm": 1.055484414100647, "learning_rate": 0.0002, "epoch": 5.651105651105651, "step": 4600}, {"loss": 0.3436, "grad_norm": 0.8408507704734802, "learning_rate": 0.0002, "epoch": 5.663390663390663, "step": 4610}, {"loss": 0.3619, "grad_norm": 1.0293926000595093, "learning_rate": 0.0002, "epoch": 5.675675675675675, "step": 4620}, {"loss": 0.3484, "grad_norm": 0.7198245525360107, "learning_rate": 0.0002, "epoch": 5.687960687960688, "step": 4630}, {"loss": 0.3563, "grad_norm": 0.7564466595649719, "learning_rate": 0.0002, "epoch": 5.7002457002457, "step": 4640}, {"loss": 0.3435, "grad_norm": 0.7980002760887146, "learning_rate": 0.0002, "epoch": 5.712530712530713, "step": 4650}, {"loss": 0.3478, "grad_norm": 0.8685088753700256, "learning_rate": 0.0002, "epoch": 5.724815724815725, "step": 4660}, {"loss": 0.3692, "grad_norm": 0.8816949129104614, "learning_rate": 0.0002, "epoch": 5.737100737100737, "step": 4670}, {"loss": 0.3462, "grad_norm": 0.7154731750488281, "learning_rate": 0.0002, "epoch": 5.749385749385749, "step": 4680}, {"loss": 0.3503, "grad_norm": 0.9430679678916931, "learning_rate": 0.0002, "epoch": 5.761670761670762, "step": 4690}, {"loss": 0.3439, "grad_norm": 0.7640151381492615, "learning_rate": 0.0002, "epoch": 5.773955773955774, "step": 4700}, {"loss": 0.3444, "grad_norm": 1.0920690298080444, "learning_rate": 0.0002, "epoch": 5.7862407862407865, "step": 4710}, {"loss": 0.3356, "grad_norm": 0.9362104535102844, "learning_rate": 0.0002, "epoch": 5.798525798525798, "step": 4720}, {"loss": 0.339, "grad_norm": 0.8392294645309448, "learning_rate": 0.0002, "epoch": 5.8108108108108105, "step": 4730}, {"loss": 0.3488, "grad_norm": 0.9893582463264465, "learning_rate": 0.0002, "epoch": 5.823095823095823, "step": 4740}, {"loss": 0.3446, "grad_norm": 0.6985510587692261, "learning_rate": 0.0002, "epoch": 5.835380835380835, "step": 4750}, {"loss": 0.3534, "grad_norm": 0.8906862735748291, "learning_rate": 0.0002, "epoch": 5.847665847665848, "step": 4760}, {"loss": 0.3481, "grad_norm": 0.8036413192749023, "learning_rate": 0.0002, "epoch": 5.85995085995086, "step": 4770}, {"loss": 0.3326, "grad_norm": 0.9948155283927917, "learning_rate": 0.0002, "epoch": 5.872235872235873, "step": 4780}, {"loss": 0.3385, "grad_norm": 0.8618432283401489, "learning_rate": 0.0002, "epoch": 5.884520884520884, "step": 4790}, {"loss": 0.3302, "grad_norm": 1.0422909259796143, "learning_rate": 0.0002, "epoch": 5.896805896805897, "step": 4800}, {"loss": 0.3448, "grad_norm": 1.1892569065093994, "learning_rate": 0.0002, "epoch": 5.909090909090909, "step": 4810}, {"loss": 0.3506, "grad_norm": 1.1459916830062866, "learning_rate": 0.0002, "epoch": 5.921375921375922, "step": 4820}, {"loss": 0.3387, "grad_norm": 1.056235909461975, "learning_rate": 0.0002, "epoch": 5.933660933660933, "step": 4830}, {"loss": 0.344, "grad_norm": 0.8517277240753174, "learning_rate": 0.0002, "epoch": 5.945945945945946, "step": 4840}, {"loss": 0.3421, "grad_norm": 0.8153380751609802, "learning_rate": 0.0002, "epoch": 5.958230958230958, "step": 4850}, {"loss": 0.3409, "grad_norm": 0.7907533049583435, "learning_rate": 0.0002, "epoch": 5.9705159705159705, "step": 4860}, {"loss": 0.3337, "grad_norm": 0.8443069458007812, "learning_rate": 0.0002, "epoch": 5.982800982800983, "step": 4870}, {"loss": 0.3351, "grad_norm": 0.8711344003677368, "learning_rate": 0.0002, "epoch": 5.995085995085995, "step": 4880}, {"eval_loss": 0.3778059184551239, "eval_runtime": 20.6858, "eval_samples_per_second": 16.001, "eval_steps_per_second": 2.03, "epoch": 6.0, "step": 4884}, {"loss": 0.3244, "grad_norm": 0.7697948813438416, "learning_rate": 0.0002, "epoch": 6.007371007371007, "step": 4890}, {"loss": 0.3118, "grad_norm": 0.7734108567237854, "learning_rate": 0.0002, "epoch": 6.019656019656019, "step": 4900}, {"loss": 0.3242, "grad_norm": 0.7173922657966614, "learning_rate": 0.0002, "epoch": 6.031941031941032, "step": 4910}, {"loss": 0.3159, "grad_norm": 1.062118649482727, "learning_rate": 0.0002, "epoch": 6.044226044226044, "step": 4920}, {"loss": 0.3361, "grad_norm": 0.746422529220581, "learning_rate": 0.0002, "epoch": 6.056511056511057, "step": 4930}, {"loss": 0.3204, "grad_norm": 0.8549448251724243, "learning_rate": 0.0002, "epoch": 6.068796068796069, "step": 4940}, {"loss": 0.3236, "grad_norm": 0.9405432939529419, "learning_rate": 0.0002, "epoch": 6.081081081081081, "step": 4950}, {"loss": 0.3278, "grad_norm": 0.752382755279541, "learning_rate": 0.0002, "epoch": 6.093366093366093, "step": 4960}, {"loss": 0.3204, "grad_norm": 0.820332407951355, "learning_rate": 0.0002, "epoch": 6.105651105651106, "step": 4970}, {"loss": 0.3192, "grad_norm": 0.8701449036598206, "learning_rate": 0.0002, "epoch": 6.117936117936118, "step": 4980}, {"loss": 0.321, "grad_norm": 0.8192865252494812, "learning_rate": 0.0002, "epoch": 6.1302211302211305, "step": 4990}, {"loss": 0.3295, "grad_norm": 1.0016303062438965, "learning_rate": 0.0002, "epoch": 6.142506142506143, "step": 5000}, {"loss": 0.3352, "grad_norm": 0.9194409251213074, "learning_rate": 0.0002, "epoch": 6.1547911547911545, "step": 5010}, {"loss": 0.3205, "grad_norm": 0.9319757223129272, "learning_rate": 0.0002, "epoch": 6.167076167076167, "step": 5020}, {"loss": 0.3256, "grad_norm": 0.8737656474113464, "learning_rate": 0.0002, "epoch": 6.179361179361179, "step": 5030}, {"loss": 0.3221, "grad_norm": 0.8736537098884583, "learning_rate": 0.0002, "epoch": 6.191646191646192, "step": 5040}, {"loss": 0.3265, "grad_norm": 0.9301430583000183, "learning_rate": 0.0002, "epoch": 6.203931203931204, "step": 5050}, {"loss": 0.3285, "grad_norm": 0.7717130780220032, "learning_rate": 0.0002, "epoch": 6.216216216216216, "step": 5060}, {"loss": 0.3192, "grad_norm": 0.6709604859352112, "learning_rate": 0.0002, "epoch": 6.228501228501228, "step": 5070}, {"loss": 0.3352, "grad_norm": 0.879374086856842, "learning_rate": 0.0002, "epoch": 6.240786240786241, "step": 5080}, {"loss": 0.329, "grad_norm": 0.9136955738067627, "learning_rate": 0.0002, "epoch": 6.253071253071253, "step": 5090}, {"loss": 0.3228, "grad_norm": 0.795177161693573, "learning_rate": 0.0002, "epoch": 6.2653562653562656, "step": 5100}, {"loss": 0.3273, "grad_norm": 1.0412259101867676, "learning_rate": 0.0002, "epoch": 6.277641277641278, "step": 5110}, {"loss": 0.3221, "grad_norm": 0.7382524013519287, "learning_rate": 0.0002, "epoch": 6.2899262899262895, "step": 5120}, {"loss": 0.3102, "grad_norm": 0.8818480968475342, "learning_rate": 0.0002, "epoch": 6.302211302211302, "step": 5130}, {"loss": 0.3316, "grad_norm": 0.7865153551101685, "learning_rate": 0.0002, "epoch": 6.314496314496314, "step": 5140}, {"loss": 0.3264, "grad_norm": 0.9166486859321594, "learning_rate": 0.0002, "epoch": 6.326781326781327, "step": 5150}, {"loss": 0.33, "grad_norm": 0.6655149459838867, "learning_rate": 0.0002, "epoch": 6.339066339066339, "step": 5160}, {"loss": 0.3359, "grad_norm": 0.7762818336486816, "learning_rate": 0.0002, "epoch": 6.351351351351352, "step": 5170}, {"loss": 0.3244, "grad_norm": 0.8057235479354858, "learning_rate": 0.0002, "epoch": 6.363636363636363, "step": 5180}, {"loss": 0.3167, "grad_norm": 0.8186984062194824, "learning_rate": 0.0002, "epoch": 6.375921375921376, "step": 5190}, {"loss": 0.3289, "grad_norm": 0.8669573068618774, "learning_rate": 0.0002, "epoch": 6.388206388206388, "step": 5200}, {"loss": 0.3313, "grad_norm": 0.8904402852058411, "learning_rate": 0.0002, "epoch": 6.400491400491401, "step": 5210}, {"loss": 0.3187, "grad_norm": 0.9250359535217285, "learning_rate": 0.0002, "epoch": 6.412776412776413, "step": 5220}, {"loss": 0.3229, "grad_norm": 0.8718299269676208, "learning_rate": 0.0002, "epoch": 6.4250614250614255, "step": 5230}, {"loss": 0.3214, "grad_norm": 0.8156430125236511, "learning_rate": 0.0002, "epoch": 6.437346437346437, "step": 5240}, {"loss": 0.3244, "grad_norm": 0.7759218215942383, "learning_rate": 0.0002, "epoch": 6.4496314496314495, "step": 5250}, {"loss": 0.3298, "grad_norm": 0.8137310743331909, "learning_rate": 0.0002, "epoch": 6.461916461916462, "step": 5260}, {"loss": 0.3275, "grad_norm": 0.8121917843818665, "learning_rate": 0.0002, "epoch": 6.474201474201474, "step": 5270}, {"loss": 0.3201, "grad_norm": 0.8178010582923889, "learning_rate": 0.0002, "epoch": 6.486486486486487, "step": 5280}, {"loss": 0.3271, "grad_norm": 1.1806302070617676, "learning_rate": 0.0002, "epoch": 6.498771498771498, "step": 5290}, {"loss": 0.3231, "grad_norm": 0.8255127668380737, "learning_rate": 0.0002, "epoch": 6.511056511056511, "step": 5300}, {"loss": 0.3227, "grad_norm": 0.8006690740585327, "learning_rate": 0.0002, "epoch": 6.523341523341523, "step": 5310}, {"loss": 0.3262, "grad_norm": 0.9932374358177185, "learning_rate": 0.0002, "epoch": 6.535626535626536, "step": 5320}, {"loss": 0.3291, "grad_norm": 0.8973969221115112, "learning_rate": 0.0002, "epoch": 6.547911547911548, "step": 5330}, {"loss": 0.3146, "grad_norm": 0.7359915971755981, "learning_rate": 0.0002, "epoch": 6.560196560196561, "step": 5340}, {"loss": 0.3308, "grad_norm": 0.9941133856773376, "learning_rate": 0.0002, "epoch": 6.572481572481572, "step": 5350}, {"loss": 0.3202, "grad_norm": 0.9008874893188477, "learning_rate": 0.0002, "epoch": 6.584766584766585, "step": 5360}, {"loss": 0.3271, "grad_norm": 1.309710144996643, "learning_rate": 0.0002, "epoch": 6.597051597051597, "step": 5370}, {"loss": 0.3177, "grad_norm": 0.797768235206604, "learning_rate": 0.0002, "epoch": 6.6093366093366095, "step": 5380}, {"loss": 0.3218, "grad_norm": 0.8507353663444519, "learning_rate": 0.0002, "epoch": 6.621621621621622, "step": 5390}, {"loss": 0.3204, "grad_norm": 0.9628674983978271, "learning_rate": 0.0002, "epoch": 6.6339066339066335, "step": 5400}, {"loss": 0.3155, "grad_norm": 0.6989983320236206, "learning_rate": 0.0002, "epoch": 6.646191646191646, "step": 5410}, {"loss": 0.3197, "grad_norm": 0.9505863189697266, "learning_rate": 0.0002, "epoch": 6.658476658476658, "step": 5420}, {"loss": 0.3259, "grad_norm": 0.8058171272277832, "learning_rate": 0.0002, "epoch": 6.670761670761671, "step": 5430}, {"loss": 0.3248, "grad_norm": 0.8476499915122986, "learning_rate": 0.0002, "epoch": 6.683046683046683, "step": 5440}, {"loss": 0.326, "grad_norm": 0.8503309488296509, "learning_rate": 0.0002, "epoch": 6.695331695331696, "step": 5450}, {"loss": 0.3218, "grad_norm": 0.919566810131073, "learning_rate": 0.0002, "epoch": 6.707616707616707, "step": 5460}, {"loss": 0.3218, "grad_norm": 0.7741201519966125, "learning_rate": 0.0002, "epoch": 6.71990171990172, "step": 5470}, {"loss": 0.329, "grad_norm": 0.8432701826095581, "learning_rate": 0.0002, "epoch": 6.732186732186732, "step": 5480}, {"loss": 0.3284, "grad_norm": 1.0183148384094238, "learning_rate": 0.0002, "epoch": 6.744471744471745, "step": 5490}, {"loss": 0.3312, "grad_norm": 0.8491143584251404, "learning_rate": 0.0002, "epoch": 6.756756756756757, "step": 5500}, {"loss": 0.3208, "grad_norm": 0.9586310386657715, "learning_rate": 0.0002, "epoch": 6.769041769041769, "step": 5510}, {"loss": 0.3305, "grad_norm": 0.7936097383499146, "learning_rate": 0.0002, "epoch": 6.781326781326781, "step": 5520}, {"loss": 0.318, "grad_norm": 0.7875059247016907, "learning_rate": 0.0002, "epoch": 6.7936117936117935, "step": 5530}, {"loss": 0.3234, "grad_norm": 0.8136157393455505, "learning_rate": 0.0002, "epoch": 6.805896805896806, "step": 5540}, {"loss": 0.3161, "grad_norm": 0.837213933467865, "learning_rate": 0.0002, "epoch": 6.818181818181818, "step": 5550}, {"loss": 0.3153, "grad_norm": 0.6812925338745117, "learning_rate": 0.0002, "epoch": 6.830466830466831, "step": 5560}, {"loss": 0.3139, "grad_norm": 0.7309592962265015, "learning_rate": 0.0002, "epoch": 6.842751842751843, "step": 5570}, {"loss": 0.3126, "grad_norm": 0.6905979514122009, "learning_rate": 0.0002, "epoch": 6.855036855036855, "step": 5580}, {"loss": 0.3291, "grad_norm": 1.1768406629562378, "learning_rate": 0.0002, "epoch": 6.867321867321867, "step": 5590}, {"loss": 0.3193, "grad_norm": 0.7618567943572998, "learning_rate": 0.0002, "epoch": 6.87960687960688, "step": 5600}, {"loss": 0.3296, "grad_norm": 0.7930929660797119, "learning_rate": 0.0002, "epoch": 6.891891891891892, "step": 5610}, {"loss": 0.3241, "grad_norm": 0.7931787371635437, "learning_rate": 0.0002, "epoch": 6.9041769041769046, "step": 5620}, {"loss": 0.3215, "grad_norm": 0.6366972923278809, "learning_rate": 0.0002, "epoch": 6.916461916461916, "step": 5630}, {"loss": 0.3264, "grad_norm": 0.7782737612724304, "learning_rate": 0.0002, "epoch": 6.9287469287469285, "step": 5640}, {"loss": 0.3186, "grad_norm": 0.8643787503242493, "learning_rate": 0.0002, "epoch": 6.941031941031941, "step": 5650}, {"loss": 0.3285, "grad_norm": 1.0843733549118042, "learning_rate": 0.0002, "epoch": 6.953316953316953, "step": 5660}, {"loss": 0.3163, "grad_norm": 0.71319180727005, "learning_rate": 0.0002, "epoch": 6.965601965601966, "step": 5670}, {"loss": 0.3196, "grad_norm": 0.976536750793457, "learning_rate": 0.0002, "epoch": 6.977886977886978, "step": 5680}, {"loss": 0.3255, "grad_norm": 0.9221968054771423, "learning_rate": 0.0002, "epoch": 6.99017199017199, "step": 5690}]}
+{"epoch": 8.0, "step": 6512, "epoch_duration": 733.1801314353943, "total_accumulated_duration": 6005.529521942139, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 3020.60888671875}, "peak_memory_usage": {"GPU_0": 15051.17431640625}, "avg_memory_reserved": {"GPU_0": 15256.0}, "peak_memory_reserved": {"GPU_0": 16176.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-15098-sd-1/checkpoint-5698", "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": 3.5354, "grad_norm": 0.8178550004959106, "learning_rate": 0.0002, "epoch": 0.012285012285012284, "step": 10}, {"loss": 2.534, "grad_norm": 1.0338047742843628, "learning_rate": 0.0002, "epoch": 0.02457002457002457, "step": 20}, {"loss": 2.1691, "grad_norm": 0.8931729197502136, "learning_rate": 0.0002, "epoch": 0.036855036855036855, "step": 30}, {"loss": 1.8813, "grad_norm": 0.9666458964347839, "learning_rate": 0.0002, "epoch": 0.04914004914004914, "step": 40}, {"loss": 1.6479, "grad_norm": 1.2691702842712402, "learning_rate": 0.0002, "epoch": 0.06142506142506143, "step": 50}, {"loss": 1.3831, "grad_norm": 1.0307111740112305, "learning_rate": 0.0002, "epoch": 0.07371007371007371, "step": 60}, {"loss": 1.2987, "grad_norm": 1.1837389469146729, "learning_rate": 0.0002, "epoch": 0.085995085995086, "step": 70}, {"loss": 1.2325, "grad_norm": 1.1481467485427856, "learning_rate": 0.0002, "epoch": 0.09828009828009827, "step": 80}, {"loss": 1.1425, "grad_norm": 1.0385297536849976, "learning_rate": 0.0002, "epoch": 0.11056511056511056, "step": 90}, {"loss": 1.1177, "grad_norm": 1.125789999961853, "learning_rate": 0.0002, "epoch": 0.12285012285012285, "step": 100}, {"loss": 1.0477, "grad_norm": 0.9630613923072815, "learning_rate": 0.0002, "epoch": 0.13513513513513514, "step": 110}, {"loss": 1.0074, "grad_norm": 1.060392141342163, "learning_rate": 0.0002, "epoch": 0.14742014742014742, "step": 120}, {"loss": 1.0128, "grad_norm": 1.0986546277999878, "learning_rate": 0.0002, "epoch": 0.1597051597051597, "step": 130}, {"loss": 1.0068, "grad_norm": 1.1713459491729736, "learning_rate": 0.0002, "epoch": 0.171990171990172, "step": 140}, {"loss": 0.973, "grad_norm": 1.1548224687576294, "learning_rate": 0.0002, "epoch": 0.18427518427518427, "step": 150}, {"loss": 0.941, "grad_norm": 1.2662502527236938, "learning_rate": 0.0002, "epoch": 0.19656019656019655, "step": 160}, {"loss": 0.8849, "grad_norm": 1.1521110534667969, "learning_rate": 0.0002, "epoch": 0.20884520884520885, "step": 170}, {"loss": 0.8931, "grad_norm": 1.1044857501983643, "learning_rate": 0.0002, "epoch": 0.22113022113022113, "step": 180}, {"loss": 0.9572, "grad_norm": 0.9770650267601013, "learning_rate": 0.0002, "epoch": 0.2334152334152334, "step": 190}, {"loss": 0.881, "grad_norm": 0.9710931777954102, "learning_rate": 0.0002, "epoch": 0.2457002457002457, "step": 200}, {"loss": 0.9205, "grad_norm": 0.9593933820724487, "learning_rate": 0.0002, "epoch": 0.257985257985258, "step": 210}, {"loss": 0.843, "grad_norm": 1.003553032875061, "learning_rate": 0.0002, "epoch": 0.2702702702702703, "step": 220}, {"loss": 0.9032, "grad_norm": 0.9187764525413513, "learning_rate": 0.0002, "epoch": 0.28255528255528256, "step": 230}, {"loss": 0.8572, "grad_norm": 0.9294946789741516, "learning_rate": 0.0002, "epoch": 0.29484029484029484, "step": 240}, {"loss": 0.8856, "grad_norm": 0.9537560939788818, "learning_rate": 0.0002, "epoch": 0.3071253071253071, "step": 250}, {"loss": 0.8546, "grad_norm": 1.00537109375, "learning_rate": 0.0002, "epoch": 0.3194103194103194, "step": 260}, {"loss": 0.896, "grad_norm": 0.8775776028633118, "learning_rate": 0.0002, "epoch": 0.3316953316953317, "step": 270}, {"loss": 0.808, "grad_norm": 0.8316839933395386, "learning_rate": 0.0002, "epoch": 0.343980343980344, "step": 280}, {"loss": 0.8248, "grad_norm": 0.8542073965072632, "learning_rate": 0.0002, "epoch": 0.35626535626535627, "step": 290}, {"loss": 0.8452, "grad_norm": 0.848444402217865, "learning_rate": 0.0002, "epoch": 0.36855036855036855, "step": 300}, {"loss": 0.8253, "grad_norm": 0.9017520546913147, "learning_rate": 0.0002, "epoch": 0.3808353808353808, "step": 310}, {"loss": 0.8098, "grad_norm": 0.7672467231750488, "learning_rate": 0.0002, "epoch": 0.3931203931203931, "step": 320}, {"loss": 0.8478, "grad_norm": 0.9109916687011719, "learning_rate": 0.0002, "epoch": 0.40540540540540543, "step": 330}, {"loss": 0.8041, "grad_norm": 0.8750321269035339, "learning_rate": 0.0002, "epoch": 0.4176904176904177, "step": 340}, {"loss": 0.8158, "grad_norm": 0.7911098599433899, "learning_rate": 0.0002, "epoch": 0.42997542997543, "step": 350}, {"loss": 0.8001, "grad_norm": 0.871601402759552, "learning_rate": 0.0002, "epoch": 0.44226044226044225, "step": 360}, {"loss": 0.8187, "grad_norm": 0.9393917918205261, "learning_rate": 0.0002, "epoch": 0.45454545454545453, "step": 370}, {"loss": 0.8124, "grad_norm": 0.8260403275489807, "learning_rate": 0.0002, "epoch": 0.4668304668304668, "step": 380}, {"loss": 0.7768, "grad_norm": 0.9792159199714661, "learning_rate": 0.0002, "epoch": 0.47911547911547914, "step": 390}, {"loss": 0.7981, "grad_norm": 0.9943315982818604, "learning_rate": 0.0002, "epoch": 0.4914004914004914, "step": 400}, {"loss": 0.7765, "grad_norm": 0.8999950885772705, "learning_rate": 0.0002, "epoch": 0.5036855036855037, "step": 410}, {"loss": 0.7807, "grad_norm": 0.8348393440246582, "learning_rate": 0.0002, "epoch": 0.515970515970516, "step": 420}, {"loss": 0.8269, "grad_norm": 0.7371744513511658, "learning_rate": 0.0002, "epoch": 0.5282555282555282, "step": 430}, {"loss": 0.8181, "grad_norm": 0.8354107141494751, "learning_rate": 0.0002, "epoch": 0.5405405405405406, "step": 440}, {"loss": 0.7849, "grad_norm": 0.8553793430328369, "learning_rate": 0.0002, "epoch": 0.5528255528255528, "step": 450}, {"loss": 0.8098, "grad_norm": 1.0762015581130981, "learning_rate": 0.0002, "epoch": 0.5651105651105651, "step": 460}, {"loss": 0.7942, "grad_norm": 0.8350747227668762, "learning_rate": 0.0002, "epoch": 0.5773955773955773, "step": 470}, {"loss": 0.7922, "grad_norm": 0.7819945216178894, "learning_rate": 0.0002, "epoch": 0.5896805896805897, "step": 480}, {"loss": 0.7845, "grad_norm": 0.8079741597175598, "learning_rate": 0.0002, "epoch": 0.601965601965602, "step": 490}, {"loss": 0.7417, "grad_norm": 0.776435911655426, "learning_rate": 0.0002, "epoch": 0.6142506142506142, "step": 500}, {"loss": 0.7855, "grad_norm": 0.7646855115890503, "learning_rate": 0.0002, "epoch": 0.6265356265356266, "step": 510}, {"loss": 0.7923, "grad_norm": 0.786396861076355, "learning_rate": 0.0002, "epoch": 0.6388206388206388, "step": 520}, {"loss": 0.7624, "grad_norm": 0.7016594409942627, "learning_rate": 0.0002, "epoch": 0.6511056511056511, "step": 530}, {"loss": 0.786, "grad_norm": 0.8060444593429565, "learning_rate": 0.0002, "epoch": 0.6633906633906634, "step": 540}, {"loss": 0.7417, "grad_norm": 0.9087467789649963, "learning_rate": 0.0002, "epoch": 0.6756756756756757, "step": 550}, {"loss": 0.7591, "grad_norm": 0.8149628639221191, "learning_rate": 0.0002, "epoch": 0.687960687960688, "step": 560}, {"loss": 0.8004, "grad_norm": 0.7493641972541809, "learning_rate": 0.0002, "epoch": 0.7002457002457002, "step": 570}, {"loss": 0.765, "grad_norm": 0.7958765625953674, "learning_rate": 0.0002, "epoch": 0.7125307125307125, "step": 580}, {"loss": 0.7276, "grad_norm": 0.7917273640632629, "learning_rate": 0.0002, "epoch": 0.7248157248157249, "step": 590}, {"loss": 0.758, "grad_norm": 0.8040468692779541, "learning_rate": 0.0002, "epoch": 0.7371007371007371, "step": 600}, {"loss": 0.735, "grad_norm": 0.8696851134300232, "learning_rate": 0.0002, "epoch": 0.7493857493857494, "step": 610}, {"loss": 0.7321, "grad_norm": 0.8418059945106506, "learning_rate": 0.0002, "epoch": 0.7616707616707616, "step": 620}, {"loss": 0.7395, "grad_norm": 0.7754243612289429, "learning_rate": 0.0002, "epoch": 0.773955773955774, "step": 630}, {"loss": 0.7679, "grad_norm": 0.7639613747596741, "learning_rate": 0.0002, "epoch": 0.7862407862407862, "step": 640}, {"loss": 0.7159, "grad_norm": 0.7516646385192871, "learning_rate": 0.0002, "epoch": 0.7985257985257985, "step": 650}, {"loss": 0.7349, "grad_norm": 0.7840844988822937, "learning_rate": 0.0002, "epoch": 0.8108108108108109, "step": 660}, {"loss": 0.7264, "grad_norm": 0.7657070755958557, "learning_rate": 0.0002, "epoch": 0.8230958230958231, "step": 670}, {"loss": 0.7369, "grad_norm": 0.7711591720581055, "learning_rate": 0.0002, "epoch": 0.8353808353808354, "step": 680}, {"loss": 0.759, "grad_norm": 0.8026325106620789, "learning_rate": 0.0002, "epoch": 0.8476658476658476, "step": 690}, {"loss": 0.737, "grad_norm": 0.7902713418006897, "learning_rate": 0.0002, "epoch": 0.85995085995086, "step": 700}, {"loss": 0.7349, "grad_norm": 0.8212456107139587, "learning_rate": 0.0002, "epoch": 0.8722358722358723, "step": 710}, {"loss": 0.7661, "grad_norm": 0.7867200970649719, "learning_rate": 0.0002, "epoch": 0.8845208845208845, "step": 720}, {"loss": 0.7195, "grad_norm": 0.80084627866745, "learning_rate": 0.0002, "epoch": 0.8968058968058968, "step": 730}, {"loss": 0.7641, "grad_norm": 0.7203794121742249, "learning_rate": 0.0002, "epoch": 0.9090909090909091, "step": 740}, {"loss": 0.7134, "grad_norm": 0.7598419785499573, "learning_rate": 0.0002, "epoch": 0.9213759213759214, "step": 750}, {"loss": 0.7208, "grad_norm": 0.7787027359008789, "learning_rate": 0.0002, "epoch": 0.9336609336609336, "step": 760}, {"loss": 0.7119, "grad_norm": 0.8444012403488159, "learning_rate": 0.0002, "epoch": 0.9459459459459459, "step": 770}, {"loss": 0.7099, "grad_norm": 0.7388550639152527, "learning_rate": 0.0002, "epoch": 0.9582309582309583, "step": 780}, {"loss": 0.7184, "grad_norm": 0.7379167079925537, "learning_rate": 0.0002, "epoch": 0.9705159705159705, "step": 790}, {"loss": 0.7143, "grad_norm": 0.8291640281677246, "learning_rate": 0.0002, "epoch": 0.9828009828009828, "step": 800}, {"loss": 0.6972, "grad_norm": 0.7415094375610352, "learning_rate": 0.0002, "epoch": 0.995085995085995, "step": 810}, {"eval_loss": 0.703994870185852, "eval_runtime": 20.2182, "eval_samples_per_second": 16.371, "eval_steps_per_second": 2.077, "epoch": 1.0, "step": 814}, {"loss": 0.6959, "grad_norm": 0.7405961751937866, "learning_rate": 0.0002, "epoch": 1.0073710073710074, "step": 820}, {"loss": 0.6706, "grad_norm": 0.8534344434738159, "learning_rate": 0.0002, "epoch": 1.0196560196560196, "step": 830}, {"loss": 0.6719, "grad_norm": 0.7415764331817627, "learning_rate": 0.0002, "epoch": 1.031941031941032, "step": 840}, {"loss": 0.6673, "grad_norm": 0.74293053150177, "learning_rate": 0.0002, "epoch": 1.0442260442260443, "step": 850}, {"loss": 0.6897, "grad_norm": 0.697727382183075, "learning_rate": 0.0002, "epoch": 1.0565110565110565, "step": 860}, {"loss": 0.6566, "grad_norm": 0.8022570013999939, "learning_rate": 0.0002, "epoch": 1.0687960687960687, "step": 870}, {"loss": 0.6759, "grad_norm": 0.7545800805091858, "learning_rate": 0.0002, "epoch": 1.0810810810810811, "step": 880}, {"loss": 0.6397, "grad_norm": 0.8005648255348206, "learning_rate": 0.0002, "epoch": 1.0933660933660934, "step": 890}, {"loss": 0.6499, "grad_norm": 0.7681778073310852, "learning_rate": 0.0002, "epoch": 1.1056511056511056, "step": 900}, {"loss": 0.6672, "grad_norm": 0.7822468876838684, "learning_rate": 0.0002, "epoch": 1.117936117936118, "step": 910}, {"loss": 0.6492, "grad_norm": 0.8324839472770691, "learning_rate": 0.0002, "epoch": 1.1302211302211302, "step": 920}, {"loss": 0.6659, "grad_norm": 0.8206289410591125, "learning_rate": 0.0002, "epoch": 1.1425061425061425, "step": 930}, {"loss": 0.6385, "grad_norm": 0.786461591720581, "learning_rate": 0.0002, "epoch": 1.154791154791155, "step": 940}, {"loss": 0.6493, "grad_norm": 0.8288539052009583, "learning_rate": 0.0002, "epoch": 1.1670761670761671, "step": 950}, {"loss": 0.6818, "grad_norm": 0.7566865682601929, "learning_rate": 0.0002, "epoch": 1.1793611793611793, "step": 960}, {"loss": 0.6597, "grad_norm": 0.7761894464492798, "learning_rate": 0.0002, "epoch": 1.1916461916461916, "step": 970}, {"loss": 0.6403, "grad_norm": 0.7608440518379211, "learning_rate": 0.0002, "epoch": 1.203931203931204, "step": 980}, {"loss": 0.7041, "grad_norm": 0.799745500087738, "learning_rate": 0.0002, "epoch": 1.2162162162162162, "step": 990}, {"loss": 0.6358, "grad_norm": 0.8135330677032471, "learning_rate": 0.0002, "epoch": 1.2285012285012284, "step": 1000}, {"loss": 0.6496, "grad_norm": 0.7410391569137573, "learning_rate": 0.0002, "epoch": 1.2407862407862407, "step": 1010}, {"loss": 0.63, "grad_norm": 0.7826172709465027, "learning_rate": 0.0002, "epoch": 1.253071253071253, "step": 1020}, {"loss": 0.6582, "grad_norm": 0.7210677862167358, "learning_rate": 0.0002, "epoch": 1.2653562653562653, "step": 1030}, {"loss": 0.6609, "grad_norm": 0.7571766972541809, "learning_rate": 0.0002, "epoch": 1.2776412776412776, "step": 1040}, {"loss": 0.6315, "grad_norm": 0.8602666258811951, "learning_rate": 0.0002, "epoch": 1.28992628992629, "step": 1050}, {"loss": 0.6825, "grad_norm": 0.8640648722648621, "learning_rate": 0.0002, "epoch": 1.3022113022113022, "step": 1060}, {"loss": 0.6563, "grad_norm": 0.7289374470710754, "learning_rate": 0.0002, "epoch": 1.3144963144963144, "step": 1070}, {"loss": 0.629, "grad_norm": 0.8099908828735352, "learning_rate": 0.0002, "epoch": 1.3267813267813269, "step": 1080}, {"loss": 0.6882, "grad_norm": 0.8623505234718323, "learning_rate": 0.0002, "epoch": 1.339066339066339, "step": 1090}, {"loss": 0.6368, "grad_norm": 0.900576114654541, "learning_rate": 0.0002, "epoch": 1.3513513513513513, "step": 1100}, {"loss": 0.6398, "grad_norm": 0.729603111743927, "learning_rate": 0.0002, "epoch": 1.3636363636363638, "step": 1110}, {"loss": 0.6619, "grad_norm": 0.8350434303283691, "learning_rate": 0.0002, "epoch": 1.375921375921376, "step": 1120}, {"loss": 0.6447, "grad_norm": 0.8049437999725342, "learning_rate": 0.0002, "epoch": 1.3882063882063882, "step": 1130}, {"loss": 0.6336, "grad_norm": 0.8222764134407043, "learning_rate": 0.0002, "epoch": 1.4004914004914004, "step": 1140}, {"loss": 0.6453, "grad_norm": 0.7949751019477844, "learning_rate": 0.0002, "epoch": 1.4127764127764126, "step": 1150}, {"loss": 0.6246, "grad_norm": 0.8375639915466309, "learning_rate": 0.0002, "epoch": 1.425061425061425, "step": 1160}, {"loss": 0.6358, "grad_norm": 0.7261053919792175, "learning_rate": 0.0002, "epoch": 1.4373464373464373, "step": 1170}, {"loss": 0.6709, "grad_norm": 0.6918320655822754, "learning_rate": 0.0002, "epoch": 1.4496314496314495, "step": 1180}, {"loss": 0.598, "grad_norm": 0.8148727416992188, "learning_rate": 0.0002, "epoch": 1.461916461916462, "step": 1190}, {"loss": 0.6269, "grad_norm": 0.7014724612236023, "learning_rate": 0.0002, "epoch": 1.4742014742014742, "step": 1200}, {"loss": 0.617, "grad_norm": 0.8110846281051636, "learning_rate": 0.0002, "epoch": 1.4864864864864864, "step": 1210}, {"loss": 0.6633, "grad_norm": 0.8336407542228699, "learning_rate": 0.0002, "epoch": 1.4987714987714988, "step": 1220}, {"loss": 0.6028, "grad_norm": 0.826996386051178, "learning_rate": 0.0002, "epoch": 1.511056511056511, "step": 1230}, {"loss": 0.6464, "grad_norm": 0.7503120303153992, "learning_rate": 0.0002, "epoch": 1.5233415233415233, "step": 1240}, {"loss": 0.6418, "grad_norm": 0.8297192454338074, "learning_rate": 0.0002, "epoch": 1.5356265356265357, "step": 1250}, {"loss": 0.6466, "grad_norm": 0.7585996985435486, "learning_rate": 0.0002, "epoch": 1.547911547911548, "step": 1260}, {"loss": 0.6196, "grad_norm": 0.7530493140220642, "learning_rate": 0.0002, "epoch": 1.5601965601965602, "step": 1270}, {"loss": 0.6252, "grad_norm": 0.8141939640045166, "learning_rate": 0.0002, "epoch": 1.5724815724815726, "step": 1280}, {"loss": 0.6441, "grad_norm": 0.6959931254386902, "learning_rate": 0.0002, "epoch": 1.5847665847665846, "step": 1290}, {"loss": 0.6542, "grad_norm": 0.8677428364753723, "learning_rate": 0.0002, "epoch": 1.597051597051597, "step": 1300}, {"loss": 0.633, "grad_norm": 0.8527476787567139, "learning_rate": 0.0002, "epoch": 1.6093366093366095, "step": 1310}, {"loss": 0.6393, "grad_norm": 0.8462157845497131, "learning_rate": 0.0002, "epoch": 1.6216216216216215, "step": 1320}, {"loss": 0.6265, "grad_norm": 0.9371153712272644, "learning_rate": 0.0002, "epoch": 1.633906633906634, "step": 1330}, {"loss": 0.5952, "grad_norm": 0.8408344984054565, "learning_rate": 0.0002, "epoch": 1.6461916461916462, "step": 1340}, {"loss": 0.599, "grad_norm": 0.8391859531402588, "learning_rate": 0.0002, "epoch": 1.6584766584766584, "step": 1350}, {"loss": 0.6313, "grad_norm": 0.7630598545074463, "learning_rate": 0.0002, "epoch": 1.6707616707616708, "step": 1360}, {"loss": 0.5989, "grad_norm": 0.8007895350456238, "learning_rate": 0.0002, "epoch": 1.683046683046683, "step": 1370}, {"loss": 0.6094, "grad_norm": 0.7547900080680847, "learning_rate": 0.0002, "epoch": 1.6953316953316953, "step": 1380}, {"loss": 0.6335, "grad_norm": 0.7779742479324341, "learning_rate": 0.0002, "epoch": 1.7076167076167077, "step": 1390}, {"loss": 0.6078, "grad_norm": 0.712293803691864, "learning_rate": 0.0002, "epoch": 1.71990171990172, "step": 1400}, {"loss": 0.608, "grad_norm": 0.8503297567367554, "learning_rate": 0.0002, "epoch": 1.7321867321867321, "step": 1410}, {"loss": 0.6055, "grad_norm": 0.8312245607376099, "learning_rate": 0.0002, "epoch": 1.7444717444717446, "step": 1420}, {"loss": 0.5978, "grad_norm": 0.7758049368858337, "learning_rate": 0.0002, "epoch": 1.7567567567567568, "step": 1430}, {"loss": 0.5822, "grad_norm": 0.8695956468582153, "learning_rate": 0.0002, "epoch": 1.769041769041769, "step": 1440}, {"loss": 0.5955, "grad_norm": 0.7785261273384094, "learning_rate": 0.0002, "epoch": 1.7813267813267815, "step": 1450}, {"loss": 0.6177, "grad_norm": 0.7091802358627319, "learning_rate": 0.0002, "epoch": 1.7936117936117935, "step": 1460}, {"loss": 0.5811, "grad_norm": 0.774146556854248, "learning_rate": 0.0002, "epoch": 1.805896805896806, "step": 1470}, {"loss": 0.5833, "grad_norm": 0.8342524170875549, "learning_rate": 0.0002, "epoch": 1.8181818181818183, "step": 1480}, {"loss": 0.634, "grad_norm": 0.8087738156318665, "learning_rate": 0.0002, "epoch": 1.8304668304668303, "step": 1490}, {"loss": 0.5961, "grad_norm": 0.9830479621887207, "learning_rate": 0.0002, "epoch": 1.8427518427518428, "step": 1500}, {"loss": 0.6211, "grad_norm": 0.8537567853927612, "learning_rate": 0.0002, "epoch": 1.855036855036855, "step": 1510}, {"loss": 0.5767, "grad_norm": 0.8004562854766846, "learning_rate": 0.0002, "epoch": 1.8673218673218672, "step": 1520}, {"loss": 0.604, "grad_norm": 0.8161284327507019, "learning_rate": 0.0002, "epoch": 1.8796068796068797, "step": 1530}, {"loss": 0.5808, "grad_norm": 0.8688093423843384, "learning_rate": 0.0002, "epoch": 1.8918918918918919, "step": 1540}, {"loss": 0.5663, "grad_norm": 0.8287379741668701, "learning_rate": 0.0002, "epoch": 1.904176904176904, "step": 1550}, {"loss": 0.5963, "grad_norm": 0.8050342202186584, "learning_rate": 0.0002, "epoch": 1.9164619164619165, "step": 1560}, {"loss": 0.5837, "grad_norm": 0.9273895621299744, "learning_rate": 0.0002, "epoch": 1.9287469287469288, "step": 1570}, {"loss": 0.5945, "grad_norm": 0.8416891694068909, "learning_rate": 0.0002, "epoch": 1.941031941031941, "step": 1580}, {"loss": 0.5838, "grad_norm": 0.7299820184707642, "learning_rate": 0.0002, "epoch": 1.9533169533169534, "step": 1590}, {"loss": 0.6025, "grad_norm": 0.7262272834777832, "learning_rate": 0.0002, "epoch": 1.9656019656019657, "step": 1600}, {"loss": 0.5873, "grad_norm": 0.8649004697799683, "learning_rate": 0.0002, "epoch": 1.9778869778869779, "step": 1610}, {"loss": 0.5764, "grad_norm": 0.8165444731712341, "learning_rate": 0.0002, "epoch": 1.9901719901719903, "step": 1620}, {"eval_loss": 0.5858802795410156, "eval_runtime": 22.6585, "eval_samples_per_second": 14.608, "eval_steps_per_second": 1.854, "epoch": 2.0, "step": 1628}, {"loss": 0.5803, "grad_norm": 0.8142582178115845, "learning_rate": 0.0002, "epoch": 2.0024570024570023, "step": 1630}, {"loss": 0.5499, "grad_norm": 1.0637224912643433, "learning_rate": 0.0002, "epoch": 2.0147420147420148, "step": 1640}, {"loss": 0.5556, "grad_norm": 0.8923280239105225, "learning_rate": 0.0002, "epoch": 2.027027027027027, "step": 1650}, {"loss": 0.5373, "grad_norm": 0.8169175386428833, "learning_rate": 0.0002, "epoch": 2.039312039312039, "step": 1660}, {"loss": 0.552, "grad_norm": 0.8124040365219116, "learning_rate": 0.0002, "epoch": 2.0515970515970516, "step": 1670}, {"loss": 0.5259, "grad_norm": 0.9228773713111877, "learning_rate": 0.0002, "epoch": 2.063882063882064, "step": 1680}, {"loss": 0.5571, "grad_norm": 0.7216871380805969, "learning_rate": 0.0002, "epoch": 2.076167076167076, "step": 1690}, {"loss": 0.523, "grad_norm": 0.8679503202438354, "learning_rate": 0.0002, "epoch": 2.0884520884520885, "step": 1700}, {"loss": 0.5379, "grad_norm": 0.8627730011940002, "learning_rate": 0.0002, "epoch": 2.100737100737101, "step": 1710}, {"loss": 0.551, "grad_norm": 0.9175152778625488, "learning_rate": 0.0002, "epoch": 2.113022113022113, "step": 1720}, {"loss": 0.5378, "grad_norm": 0.7930372953414917, "learning_rate": 0.0002, "epoch": 2.1253071253071254, "step": 1730}, {"loss": 0.5263, "grad_norm": 0.8370155692100525, "learning_rate": 0.0002, "epoch": 2.1375921375921374, "step": 1740}, {"loss": 0.5419, "grad_norm": 0.9121434688568115, "learning_rate": 0.0002, "epoch": 2.14987714987715, "step": 1750}, {"loss": 0.5499, "grad_norm": 0.8703579306602478, "learning_rate": 0.0002, "epoch": 2.1621621621621623, "step": 1760}, {"loss": 0.5333, "grad_norm": 0.9270512461662292, "learning_rate": 0.0002, "epoch": 2.1744471744471743, "step": 1770}, {"loss": 0.5165, "grad_norm": 0.9372949600219727, "learning_rate": 0.0002, "epoch": 2.1867321867321867, "step": 1780}, {"loss": 0.5327, "grad_norm": 0.8955178260803223, "learning_rate": 0.0002, "epoch": 2.199017199017199, "step": 1790}, {"loss": 0.5356, "grad_norm": 0.846102237701416, "learning_rate": 0.0002, "epoch": 2.211302211302211, "step": 1800}, {"loss": 0.5303, "grad_norm": 0.9186713099479675, "learning_rate": 0.0002, "epoch": 2.2235872235872236, "step": 1810}, {"loss": 0.5223, "grad_norm": 0.7695123553276062, "learning_rate": 0.0002, "epoch": 2.235872235872236, "step": 1820}, {"loss": 0.5161, "grad_norm": 0.7340332865715027, "learning_rate": 0.0002, "epoch": 2.248157248157248, "step": 1830}, {"loss": 0.5327, "grad_norm": 0.8933137655258179, "learning_rate": 0.0002, "epoch": 2.2604422604422605, "step": 1840}, {"loss": 0.5471, "grad_norm": 0.7705038189888, "learning_rate": 0.0002, "epoch": 2.2727272727272725, "step": 1850}, {"loss": 0.5346, "grad_norm": 0.8396083116531372, "learning_rate": 0.0002, "epoch": 2.285012285012285, "step": 1860}, {"loss": 0.5335, "grad_norm": 0.7695736289024353, "learning_rate": 0.0002, "epoch": 2.2972972972972974, "step": 1870}, {"loss": 0.5105, "grad_norm": 0.8535045385360718, "learning_rate": 0.0002, "epoch": 2.30958230958231, "step": 1880}, {"loss": 0.5202, "grad_norm": 0.8549142479896545, "learning_rate": 0.0002, "epoch": 2.321867321867322, "step": 1890}, {"loss": 0.5268, "grad_norm": 0.9124433994293213, "learning_rate": 0.0002, "epoch": 2.3341523341523343, "step": 1900}, {"loss": 0.506, "grad_norm": 0.855523943901062, "learning_rate": 0.0002, "epoch": 2.3464373464373462, "step": 1910}, {"loss": 0.5162, "grad_norm": 0.810878336429596, "learning_rate": 0.0002, "epoch": 2.3587223587223587, "step": 1920}, {"loss": 0.531, "grad_norm": 0.7409024834632874, "learning_rate": 0.0002, "epoch": 2.371007371007371, "step": 1930}, {"loss": 0.5045, "grad_norm": 0.8080927729606628, "learning_rate": 0.0002, "epoch": 2.383292383292383, "step": 1940}, {"loss": 0.5032, "grad_norm": 0.9661469459533691, "learning_rate": 0.0002, "epoch": 2.3955773955773956, "step": 1950}, {"loss": 0.5019, "grad_norm": 0.838766872882843, "learning_rate": 0.0002, "epoch": 2.407862407862408, "step": 1960}, {"loss": 0.5128, "grad_norm": 0.8737491965293884, "learning_rate": 0.0002, "epoch": 2.42014742014742, "step": 1970}, {"loss": 0.5153, "grad_norm": 0.8657792210578918, "learning_rate": 0.0002, "epoch": 2.4324324324324325, "step": 1980}, {"loss": 0.5665, "grad_norm": 0.8883858919143677, "learning_rate": 0.0002, "epoch": 2.444717444717445, "step": 1990}, {"loss": 0.5283, "grad_norm": 0.8647662997245789, "learning_rate": 0.0002, "epoch": 2.457002457002457, "step": 2000}, {"loss": 0.518, "grad_norm": 0.896037757396698, "learning_rate": 0.0002, "epoch": 2.4692874692874693, "step": 2010}, {"loss": 0.5245, "grad_norm": 0.8079167008399963, "learning_rate": 0.0002, "epoch": 2.4815724815724813, "step": 2020}, {"loss": 0.5311, "grad_norm": 1.0293292999267578, "learning_rate": 0.0002, "epoch": 2.493857493857494, "step": 2030}, {"loss": 0.5091, "grad_norm": 0.8459244966506958, "learning_rate": 0.0002, "epoch": 2.506142506142506, "step": 2040}, {"loss": 0.4922, "grad_norm": 0.9244982600212097, "learning_rate": 0.0002, "epoch": 2.5184275184275187, "step": 2050}, {"loss": 0.5006, "grad_norm": 0.8245007991790771, "learning_rate": 0.0002, "epoch": 2.5307125307125307, "step": 2060}, {"loss": 0.5229, "grad_norm": 0.8869297504425049, "learning_rate": 0.0002, "epoch": 2.542997542997543, "step": 2070}, {"loss": 0.5097, "grad_norm": 0.8620884418487549, "learning_rate": 0.0002, "epoch": 2.555282555282555, "step": 2080}, {"loss": 0.5239, "grad_norm": 0.8387904167175293, "learning_rate": 0.0002, "epoch": 2.5675675675675675, "step": 2090}, {"loss": 0.4974, "grad_norm": 0.8353935480117798, "learning_rate": 0.0002, "epoch": 2.57985257985258, "step": 2100}, {"loss": 0.5038, "grad_norm": 1.0136934518814087, "learning_rate": 0.0002, "epoch": 2.592137592137592, "step": 2110}, {"loss": 0.513, "grad_norm": 0.9387392997741699, "learning_rate": 0.0002, "epoch": 2.6044226044226044, "step": 2120}, {"loss": 0.4971, "grad_norm": 0.898697555065155, "learning_rate": 0.0002, "epoch": 2.616707616707617, "step": 2130}, {"loss": 0.4981, "grad_norm": 1.0145231485366821, "learning_rate": 0.0002, "epoch": 2.628992628992629, "step": 2140}, {"loss": 0.5151, "grad_norm": 0.8335273265838623, "learning_rate": 0.0002, "epoch": 2.6412776412776413, "step": 2150}, {"loss": 0.5129, "grad_norm": 1.0198529958724976, "learning_rate": 0.0002, "epoch": 2.6535626535626538, "step": 2160}, {"loss": 0.5156, "grad_norm": 0.8353323340415955, "learning_rate": 0.0002, "epoch": 2.6658476658476657, "step": 2170}, {"loss": 0.4818, "grad_norm": 0.8831406831741333, "learning_rate": 0.0002, "epoch": 2.678132678132678, "step": 2180}, {"loss": 0.4858, "grad_norm": 0.7182748913764954, "learning_rate": 0.0002, "epoch": 2.69041769041769, "step": 2190}, {"loss": 0.53, "grad_norm": 0.7892552614212036, "learning_rate": 0.0002, "epoch": 2.7027027027027026, "step": 2200}, {"loss": 0.5101, "grad_norm": 1.0144033432006836, "learning_rate": 0.0002, "epoch": 2.714987714987715, "step": 2210}, {"loss": 0.4909, "grad_norm": 1.0913645029067993, "learning_rate": 0.0002, "epoch": 2.7272727272727275, "step": 2220}, {"loss": 0.5069, "grad_norm": 1.014394998550415, "learning_rate": 0.0002, "epoch": 2.7395577395577395, "step": 2230}, {"loss": 0.4985, "grad_norm": 0.8118020296096802, "learning_rate": 0.0002, "epoch": 2.751842751842752, "step": 2240}, {"loss": 0.5088, "grad_norm": 0.9027737379074097, "learning_rate": 0.0002, "epoch": 2.764127764127764, "step": 2250}, {"loss": 0.5027, "grad_norm": 0.8017747402191162, "learning_rate": 0.0002, "epoch": 2.7764127764127764, "step": 2260}, {"loss": 0.4957, "grad_norm": 0.788362979888916, "learning_rate": 0.0002, "epoch": 2.788697788697789, "step": 2270}, {"loss": 0.5047, "grad_norm": 0.8338918089866638, "learning_rate": 0.0002, "epoch": 2.800982800982801, "step": 2280}, {"loss": 0.4925, "grad_norm": 0.8773167729377747, "learning_rate": 0.0002, "epoch": 2.8132678132678133, "step": 2290}, {"loss": 0.4806, "grad_norm": 0.9319674372673035, "learning_rate": 0.0002, "epoch": 2.8255528255528253, "step": 2300}, {"loss": 0.4815, "grad_norm": 0.8632726073265076, "learning_rate": 0.0002, "epoch": 2.8378378378378377, "step": 2310}, {"loss": 0.4842, "grad_norm": 0.785464882850647, "learning_rate": 0.0002, "epoch": 2.85012285012285, "step": 2320}, {"loss": 0.4867, "grad_norm": 0.8159732818603516, "learning_rate": 0.0002, "epoch": 2.8624078624078626, "step": 2330}, {"loss": 0.4796, "grad_norm": 0.8702368140220642, "learning_rate": 0.0002, "epoch": 2.8746928746928746, "step": 2340}, {"loss": 0.474, "grad_norm": 1.0456738471984863, "learning_rate": 0.0002, "epoch": 2.886977886977887, "step": 2350}, {"loss": 0.4934, "grad_norm": 1.0855203866958618, "learning_rate": 0.0002, "epoch": 2.899262899262899, "step": 2360}, {"loss": 0.4758, "grad_norm": 0.9378156065940857, "learning_rate": 0.0002, "epoch": 2.9115479115479115, "step": 2370}, {"loss": 0.4831, "grad_norm": 0.7390182018280029, "learning_rate": 0.0002, "epoch": 2.923832923832924, "step": 2380}, {"loss": 0.5066, "grad_norm": 0.7667133212089539, "learning_rate": 0.0002, "epoch": 2.9361179361179364, "step": 2390}, {"loss": 0.4722, "grad_norm": 0.8633476495742798, "learning_rate": 0.0002, "epoch": 2.9484029484029484, "step": 2400}, {"loss": 0.4993, "grad_norm": 1.0821104049682617, "learning_rate": 0.0002, "epoch": 2.960687960687961, "step": 2410}, {"loss": 0.4882, "grad_norm": 0.8911418914794922, "learning_rate": 0.0002, "epoch": 2.972972972972973, "step": 2420}, {"loss": 0.4819, "grad_norm": 0.8791135549545288, "learning_rate": 0.0002, "epoch": 2.9852579852579852, "step": 2430}, {"loss": 0.4875, "grad_norm": 0.8066530823707581, "learning_rate": 0.0002, "epoch": 2.9975429975429977, "step": 2440}, {"eval_loss": 0.49752503633499146, "eval_runtime": 20.2911, "eval_samples_per_second": 16.313, "eval_steps_per_second": 2.07, "epoch": 3.0, "step": 2442}, {"loss": 0.4362, "grad_norm": 0.7644656896591187, "learning_rate": 0.0002, "epoch": 3.0098280098280097, "step": 2450}, {"loss": 0.4363, "grad_norm": 0.9077525734901428, "learning_rate": 0.0002, "epoch": 3.022113022113022, "step": 2460}, {"loss": 0.422, "grad_norm": 0.7859287261962891, "learning_rate": 0.0002, "epoch": 3.0343980343980346, "step": 2470}, {"loss": 0.4574, "grad_norm": 1.1200323104858398, "learning_rate": 0.0002, "epoch": 3.0466830466830466, "step": 2480}, {"loss": 0.4519, "grad_norm": 0.7570453882217407, "learning_rate": 0.0002, "epoch": 3.058968058968059, "step": 2490}, {"loss": 0.4351, "grad_norm": 0.9450915455818176, "learning_rate": 0.0002, "epoch": 3.0712530712530715, "step": 2500}, {"loss": 0.4343, "grad_norm": 0.8303545117378235, "learning_rate": 0.0002, "epoch": 3.0835380835380835, "step": 2510}, {"loss": 0.4308, "grad_norm": 0.8864443898200989, "learning_rate": 0.0002, "epoch": 3.095823095823096, "step": 2520}, {"loss": 0.4601, "grad_norm": 0.945324718952179, "learning_rate": 0.0002, "epoch": 3.108108108108108, "step": 2530}, {"loss": 0.4345, "grad_norm": 1.0562494993209839, "learning_rate": 0.0002, "epoch": 3.1203931203931203, "step": 2540}, {"loss": 0.4375, "grad_norm": 0.8607500195503235, "learning_rate": 0.0002, "epoch": 3.1326781326781328, "step": 2550}, {"loss": 0.456, "grad_norm": 0.8719640374183655, "learning_rate": 0.0002, "epoch": 3.1449631449631448, "step": 2560}, {"loss": 0.4469, "grad_norm": 0.8647059202194214, "learning_rate": 0.0002, "epoch": 3.157248157248157, "step": 2570}, {"loss": 0.4483, "grad_norm": 0.8346507549285889, "learning_rate": 0.0002, "epoch": 3.1695331695331697, "step": 2580}, {"loss": 0.4331, "grad_norm": 1.0208854675292969, "learning_rate": 0.0002, "epoch": 3.1818181818181817, "step": 2590}, {"loss": 0.435, "grad_norm": 0.7064385414123535, "learning_rate": 0.0002, "epoch": 3.194103194103194, "step": 2600}, {"loss": 0.4541, "grad_norm": 0.927347719669342, "learning_rate": 0.0002, "epoch": 3.2063882063882065, "step": 2610}, {"loss": 0.4561, "grad_norm": 0.943517804145813, "learning_rate": 0.0002, "epoch": 3.2186732186732185, "step": 2620}, {"loss": 0.4225, "grad_norm": 0.7837198376655579, "learning_rate": 0.0002, "epoch": 3.230958230958231, "step": 2630}, {"loss": 0.4494, "grad_norm": 0.7752765417098999, "learning_rate": 0.0002, "epoch": 3.2432432432432434, "step": 2640}, {"loss": 0.4468, "grad_norm": 0.8578953146934509, "learning_rate": 0.0002, "epoch": 3.2555282555282554, "step": 2650}, {"loss": 0.4393, "grad_norm": 1.0209529399871826, "learning_rate": 0.0002, "epoch": 3.267813267813268, "step": 2660}, {"loss": 0.4517, "grad_norm": 0.9069030284881592, "learning_rate": 0.0002, "epoch": 3.2800982800982803, "step": 2670}, {"loss": 0.4262, "grad_norm": 0.8454729318618774, "learning_rate": 0.0002, "epoch": 3.2923832923832923, "step": 2680}, {"loss": 0.4349, "grad_norm": 0.8253099322319031, "learning_rate": 0.0002, "epoch": 3.3046683046683047, "step": 2690}, {"loss": 0.4503, "grad_norm": 0.8765934109687805, "learning_rate": 0.0002, "epoch": 3.3169533169533167, "step": 2700}, {"loss": 0.4518, "grad_norm": 0.8149126172065735, "learning_rate": 0.0002, "epoch": 3.329238329238329, "step": 2710}, {"loss": 0.4437, "grad_norm": 0.8820102214813232, "learning_rate": 0.0002, "epoch": 3.3415233415233416, "step": 2720}, {"loss": 0.4346, "grad_norm": 0.8813952803611755, "learning_rate": 0.0002, "epoch": 3.3538083538083536, "step": 2730}, {"loss": 0.4396, "grad_norm": 1.0338447093963623, "learning_rate": 0.0002, "epoch": 3.366093366093366, "step": 2740}, {"loss": 0.4468, "grad_norm": 0.8780209422111511, "learning_rate": 0.0002, "epoch": 3.3783783783783785, "step": 2750}, {"loss": 0.441, "grad_norm": 0.9017151594161987, "learning_rate": 0.0002, "epoch": 3.3906633906633905, "step": 2760}, {"loss": 0.446, "grad_norm": 0.8647638559341431, "learning_rate": 0.0002, "epoch": 3.402948402948403, "step": 2770}, {"loss": 0.4131, "grad_norm": 0.8298183679580688, "learning_rate": 0.0002, "epoch": 3.4152334152334154, "step": 2780}, {"loss": 0.4406, "grad_norm": 0.9298108816146851, "learning_rate": 0.0002, "epoch": 3.4275184275184274, "step": 2790}, {"loss": 0.4145, "grad_norm": 0.8909980058670044, "learning_rate": 0.0002, "epoch": 3.43980343980344, "step": 2800}, {"loss": 0.4148, "grad_norm": 0.8027496933937073, "learning_rate": 0.0002, "epoch": 3.4520884520884523, "step": 2810}, {"loss": 0.4244, "grad_norm": 0.8766195774078369, "learning_rate": 0.0002, "epoch": 3.4643734643734643, "step": 2820}, {"loss": 0.4292, "grad_norm": 0.8194443583488464, "learning_rate": 0.0002, "epoch": 3.4766584766584767, "step": 2830}, {"loss": 0.4305, "grad_norm": 0.9862873554229736, "learning_rate": 0.0002, "epoch": 3.488943488943489, "step": 2840}, {"loss": 0.4393, "grad_norm": 0.8755377531051636, "learning_rate": 0.0002, "epoch": 3.501228501228501, "step": 2850}, {"loss": 0.4231, "grad_norm": 0.7300266027450562, "learning_rate": 0.0002, "epoch": 3.5135135135135136, "step": 2860}, {"loss": 0.4278, "grad_norm": 0.8342461585998535, "learning_rate": 0.0002, "epoch": 3.5257985257985256, "step": 2870}, {"loss": 0.4395, "grad_norm": 0.8624151349067688, "learning_rate": 0.0002, "epoch": 3.538083538083538, "step": 2880}, {"loss": 0.4064, "grad_norm": 0.8931261301040649, "learning_rate": 0.0002, "epoch": 3.5503685503685505, "step": 2890}, {"loss": 0.4358, "grad_norm": 0.8617086410522461, "learning_rate": 0.0002, "epoch": 3.562653562653563, "step": 2900}, {"loss": 0.419, "grad_norm": 0.8754099607467651, "learning_rate": 0.0002, "epoch": 3.574938574938575, "step": 2910}, {"loss": 0.4275, "grad_norm": 0.8345834612846375, "learning_rate": 0.0002, "epoch": 3.5872235872235874, "step": 2920}, {"loss": 0.4375, "grad_norm": 1.1414062976837158, "learning_rate": 0.0002, "epoch": 3.5995085995085994, "step": 2930}, {"loss": 0.4297, "grad_norm": 0.994860053062439, "learning_rate": 0.0002, "epoch": 3.611793611793612, "step": 2940}, {"loss": 0.4386, "grad_norm": 1.19268000125885, "learning_rate": 0.0002, "epoch": 3.6240786240786242, "step": 2950}, {"loss": 0.4029, "grad_norm": 0.8399543762207031, "learning_rate": 0.0002, "epoch": 3.6363636363636362, "step": 2960}, {"loss": 0.4432, "grad_norm": 0.9873217940330505, "learning_rate": 0.0002, "epoch": 3.6486486486486487, "step": 2970}, {"loss": 0.4308, "grad_norm": 0.9116013646125793, "learning_rate": 0.0002, "epoch": 3.6609336609336607, "step": 2980}, {"loss": 0.4275, "grad_norm": 0.9503833651542664, "learning_rate": 0.0002, "epoch": 3.673218673218673, "step": 2990}, {"loss": 0.4306, "grad_norm": 0.9401112794876099, "learning_rate": 0.0002, "epoch": 3.6855036855036856, "step": 3000}, {"loss": 0.4333, "grad_norm": 1.00745689868927, "learning_rate": 0.0002, "epoch": 3.697788697788698, "step": 3010}, {"loss": 0.432, "grad_norm": 1.0553191900253296, "learning_rate": 0.0002, "epoch": 3.71007371007371, "step": 3020}, {"loss": 0.4321, "grad_norm": 1.0226953029632568, "learning_rate": 0.0002, "epoch": 3.7223587223587224, "step": 3030}, {"loss": 0.418, "grad_norm": 1.085554838180542, "learning_rate": 0.0002, "epoch": 3.7346437346437344, "step": 3040}, {"loss": 0.4196, "grad_norm": 0.9948731064796448, "learning_rate": 0.0002, "epoch": 3.746928746928747, "step": 3050}, {"loss": 0.4281, "grad_norm": 0.9328727126121521, "learning_rate": 0.0002, "epoch": 3.7592137592137593, "step": 3060}, {"loss": 0.4284, "grad_norm": 1.0533266067504883, "learning_rate": 0.0002, "epoch": 3.7714987714987718, "step": 3070}, {"loss": 0.4414, "grad_norm": 0.8213809132575989, "learning_rate": 0.0002, "epoch": 3.7837837837837838, "step": 3080}, {"loss": 0.4348, "grad_norm": 0.8941594362258911, "learning_rate": 0.0002, "epoch": 3.796068796068796, "step": 3090}, {"loss": 0.4266, "grad_norm": 0.8324518203735352, "learning_rate": 0.0002, "epoch": 3.808353808353808, "step": 3100}, {"loss": 0.4227, "grad_norm": 0.8811233639717102, "learning_rate": 0.0002, "epoch": 3.8206388206388207, "step": 3110}, {"loss": 0.4195, "grad_norm": 0.8781470060348511, "learning_rate": 0.0002, "epoch": 3.832923832923833, "step": 3120}, {"loss": 0.4277, "grad_norm": 0.8994116187095642, "learning_rate": 0.0002, "epoch": 3.845208845208845, "step": 3130}, {"loss": 0.4149, "grad_norm": 0.8605017066001892, "learning_rate": 0.0002, "epoch": 3.8574938574938575, "step": 3140}, {"loss": 0.4023, "grad_norm": 0.8966400027275085, "learning_rate": 0.0002, "epoch": 3.8697788697788695, "step": 3150}, {"loss": 0.4245, "grad_norm": 0.8856554627418518, "learning_rate": 0.0002, "epoch": 3.882063882063882, "step": 3160}, {"loss": 0.4101, "grad_norm": 0.8971620798110962, "learning_rate": 0.0002, "epoch": 3.8943488943488944, "step": 3170}, {"loss": 0.3993, "grad_norm": 0.9807813167572021, "learning_rate": 0.0002, "epoch": 3.906633906633907, "step": 3180}, {"loss": 0.4258, "grad_norm": 0.8614121675491333, "learning_rate": 0.0002, "epoch": 3.918918918918919, "step": 3190}, {"loss": 0.4115, "grad_norm": 0.989171028137207, "learning_rate": 0.0002, "epoch": 3.9312039312039313, "step": 3200}, {"loss": 0.4182, "grad_norm": 0.8168872594833374, "learning_rate": 0.0002, "epoch": 3.9434889434889433, "step": 3210}, {"loss": 0.4112, "grad_norm": 0.8109386563301086, "learning_rate": 0.0002, "epoch": 3.9557739557739557, "step": 3220}, {"loss": 0.4165, "grad_norm": 1.0175853967666626, "learning_rate": 0.0002, "epoch": 3.968058968058968, "step": 3230}, {"loss": 0.4146, "grad_norm": 0.936143159866333, "learning_rate": 0.0002, "epoch": 3.98034398034398, "step": 3240}, {"loss": 0.4163, "grad_norm": 0.9557915925979614, "learning_rate": 0.0002, "epoch": 3.9926289926289926, "step": 3250}, {"eval_loss": 0.4401616156101227, "eval_runtime": 20.8047, "eval_samples_per_second": 15.91, "eval_steps_per_second": 2.019, "epoch": 4.0, "step": 3256}, {"loss": 0.408, "grad_norm": 0.7590614557266235, "learning_rate": 0.0002, "epoch": 4.004914004914005, "step": 3260}, {"loss": 0.4001, "grad_norm": 0.8920791149139404, "learning_rate": 0.0002, "epoch": 4.017199017199017, "step": 3270}, {"loss": 0.3789, "grad_norm": 0.8640421628952026, "learning_rate": 0.0002, "epoch": 4.0294840294840295, "step": 3280}, {"loss": 0.3791, "grad_norm": 0.9074113965034485, "learning_rate": 0.0002, "epoch": 4.041769041769042, "step": 3290}, {"loss": 0.3728, "grad_norm": 1.0600885152816772, "learning_rate": 0.0002, "epoch": 4.054054054054054, "step": 3300}, {"loss": 0.3857, "grad_norm": 0.9682773351669312, "learning_rate": 0.0002, "epoch": 4.066339066339066, "step": 3310}, {"loss": 0.4007, "grad_norm": 0.9326395392417908, "learning_rate": 0.0002, "epoch": 4.078624078624078, "step": 3320}, {"loss": 0.3823, "grad_norm": 0.8886597156524658, "learning_rate": 0.0002, "epoch": 4.090909090909091, "step": 3330}, {"loss": 0.3929, "grad_norm": 1.032205581665039, "learning_rate": 0.0002, "epoch": 4.103194103194103, "step": 3340}, {"loss": 0.3836, "grad_norm": 0.8669408559799194, "learning_rate": 0.0002, "epoch": 4.115479115479116, "step": 3350}, {"loss": 0.3866, "grad_norm": 0.8250347971916199, "learning_rate": 0.0002, "epoch": 4.127764127764128, "step": 3360}, {"loss": 0.3826, "grad_norm": 0.7919842600822449, "learning_rate": 0.0002, "epoch": 4.14004914004914, "step": 3370}, {"loss": 0.3838, "grad_norm": 1.045682430267334, "learning_rate": 0.0002, "epoch": 4.152334152334152, "step": 3380}, {"loss": 0.3796, "grad_norm": 0.6873571276664734, "learning_rate": 0.0002, "epoch": 4.164619164619165, "step": 3390}, {"loss": 0.3942, "grad_norm": 1.0227675437927246, "learning_rate": 0.0002, "epoch": 4.176904176904177, "step": 3400}, {"loss": 0.3788, "grad_norm": 0.9167711734771729, "learning_rate": 0.0002, "epoch": 4.1891891891891895, "step": 3410}, {"loss": 0.3792, "grad_norm": 1.0598796606063843, "learning_rate": 0.0002, "epoch": 4.201474201474202, "step": 3420}, {"loss": 0.3955, "grad_norm": 0.8581843972206116, "learning_rate": 0.0002, "epoch": 4.2137592137592135, "step": 3430}, {"loss": 0.3761, "grad_norm": 0.8862360119819641, "learning_rate": 0.0002, "epoch": 4.226044226044226, "step": 3440}, {"loss": 0.3889, "grad_norm": 1.0248323678970337, "learning_rate": 0.0002, "epoch": 4.238329238329238, "step": 3450}, {"loss": 0.3827, "grad_norm": 0.8746261596679688, "learning_rate": 0.0002, "epoch": 4.250614250614251, "step": 3460}, {"loss": 0.3949, "grad_norm": 0.7442536354064941, "learning_rate": 0.0002, "epoch": 4.262899262899263, "step": 3470}, {"loss": 0.3761, "grad_norm": 0.8295119404792786, "learning_rate": 0.0002, "epoch": 4.275184275184275, "step": 3480}, {"loss": 0.3895, "grad_norm": 1.0634245872497559, "learning_rate": 0.0002, "epoch": 4.287469287469287, "step": 3490}, {"loss": 0.3955, "grad_norm": 0.9554621577262878, "learning_rate": 0.0002, "epoch": 4.2997542997543, "step": 3500}, {"loss": 0.3826, "grad_norm": 1.0191723108291626, "learning_rate": 0.0002, "epoch": 4.312039312039312, "step": 3510}, {"loss": 0.3828, "grad_norm": 0.8573611378669739, "learning_rate": 0.0002, "epoch": 4.324324324324325, "step": 3520}, {"loss": 0.3869, "grad_norm": 0.9082390069961548, "learning_rate": 0.0002, "epoch": 4.336609336609337, "step": 3530}, {"loss": 0.3902, "grad_norm": 0.8650212287902832, "learning_rate": 0.0002, "epoch": 4.348894348894349, "step": 3540}, {"loss": 0.3915, "grad_norm": 0.7186297178268433, "learning_rate": 0.0002, "epoch": 4.361179361179361, "step": 3550}, {"loss": 0.3861, "grad_norm": 0.9750986695289612, "learning_rate": 0.0002, "epoch": 4.3734643734643734, "step": 3560}, {"loss": 0.3967, "grad_norm": 1.0710467100143433, "learning_rate": 0.0002, "epoch": 4.385749385749386, "step": 3570}, {"loss": 0.3774, "grad_norm": 0.7974869012832642, "learning_rate": 0.0002, "epoch": 4.398034398034398, "step": 3580}, {"loss": 0.3738, "grad_norm": 0.9405913949012756, "learning_rate": 0.0002, "epoch": 4.41031941031941, "step": 3590}, {"loss": 0.3982, "grad_norm": 0.9393602609634399, "learning_rate": 0.0002, "epoch": 4.422604422604422, "step": 3600}, {"loss": 0.3913, "grad_norm": 1.0798007249832153, "learning_rate": 0.0002, "epoch": 4.434889434889435, "step": 3610}, {"loss": 0.3682, "grad_norm": 0.9226186275482178, "learning_rate": 0.0002, "epoch": 4.447174447174447, "step": 3620}, {"loss": 0.3742, "grad_norm": 1.1046524047851562, "learning_rate": 0.0002, "epoch": 4.45945945945946, "step": 3630}, {"loss": 0.3886, "grad_norm": 0.8848567605018616, "learning_rate": 0.0002, "epoch": 4.471744471744472, "step": 3640}, {"loss": 0.3848, "grad_norm": 0.8913224339485168, "learning_rate": 0.0002, "epoch": 4.484029484029484, "step": 3650}, {"loss": 0.3731, "grad_norm": 0.8497583270072937, "learning_rate": 0.0002, "epoch": 4.496314496314496, "step": 3660}, {"loss": 0.3804, "grad_norm": 0.8263831734657288, "learning_rate": 0.0002, "epoch": 4.5085995085995085, "step": 3670}, {"loss": 0.3815, "grad_norm": 0.8470269441604614, "learning_rate": 0.0002, "epoch": 4.520884520884521, "step": 3680}, {"loss": 0.3774, "grad_norm": 0.860038161277771, "learning_rate": 0.0002, "epoch": 4.533169533169533, "step": 3690}, {"loss": 0.3817, "grad_norm": 0.8898552656173706, "learning_rate": 0.0002, "epoch": 4.545454545454545, "step": 3700}, {"loss": 0.3776, "grad_norm": 0.8152070641517639, "learning_rate": 0.0002, "epoch": 4.557739557739557, "step": 3710}, {"loss": 0.383, "grad_norm": 0.7847675085067749, "learning_rate": 0.0002, "epoch": 4.57002457002457, "step": 3720}, {"loss": 0.3791, "grad_norm": 0.9625533819198608, "learning_rate": 0.0002, "epoch": 4.582309582309582, "step": 3730}, {"loss": 0.3699, "grad_norm": 0.9097456336021423, "learning_rate": 0.0002, "epoch": 4.594594594594595, "step": 3740}, {"loss": 0.3673, "grad_norm": 0.871329128742218, "learning_rate": 0.0002, "epoch": 4.606879606879607, "step": 3750}, {"loss": 0.3725, "grad_norm": 0.9879975914955139, "learning_rate": 0.0002, "epoch": 4.61916461916462, "step": 3760}, {"loss": 0.3827, "grad_norm": 0.8636731505393982, "learning_rate": 0.0002, "epoch": 4.631449631449631, "step": 3770}, {"loss": 0.3755, "grad_norm": 1.0488964319229126, "learning_rate": 0.0002, "epoch": 4.643734643734644, "step": 3780}, {"loss": 0.3738, "grad_norm": 0.7637056112289429, "learning_rate": 0.0002, "epoch": 4.656019656019656, "step": 3790}, {"loss": 0.3676, "grad_norm": 0.8507546186447144, "learning_rate": 0.0002, "epoch": 4.6683046683046685, "step": 3800}, {"loss": 0.3852, "grad_norm": 1.0216856002807617, "learning_rate": 0.0002, "epoch": 4.680589680589681, "step": 3810}, {"loss": 0.3751, "grad_norm": 1.026343822479248, "learning_rate": 0.0002, "epoch": 4.6928746928746925, "step": 3820}, {"loss": 0.3687, "grad_norm": 0.8311620950698853, "learning_rate": 0.0002, "epoch": 4.705159705159705, "step": 3830}, {"loss": 0.3771, "grad_norm": 0.7770653367042542, "learning_rate": 0.0002, "epoch": 4.717444717444717, "step": 3840}, {"loss": 0.37, "grad_norm": 0.7616215348243713, "learning_rate": 0.0002, "epoch": 4.72972972972973, "step": 3850}, {"loss": 0.3927, "grad_norm": 1.0377072095870972, "learning_rate": 0.0002, "epoch": 4.742014742014742, "step": 3860}, {"loss": 0.3832, "grad_norm": 0.9713505506515503, "learning_rate": 0.0002, "epoch": 4.754299754299755, "step": 3870}, {"loss": 0.3722, "grad_norm": 0.8803321719169617, "learning_rate": 0.0002, "epoch": 4.766584766584766, "step": 3880}, {"loss": 0.3756, "grad_norm": 0.885535478591919, "learning_rate": 0.0002, "epoch": 4.778869778869779, "step": 3890}, {"loss": 0.3714, "grad_norm": 1.0877983570098877, "learning_rate": 0.0002, "epoch": 4.791154791154791, "step": 3900}, {"loss": 0.3879, "grad_norm": 0.7875366806983948, "learning_rate": 0.0002, "epoch": 4.803439803439804, "step": 3910}, {"loss": 0.3591, "grad_norm": 0.8550102114677429, "learning_rate": 0.0002, "epoch": 4.815724815724816, "step": 3920}, {"loss": 0.3716, "grad_norm": 1.0217846632003784, "learning_rate": 0.0002, "epoch": 4.828009828009828, "step": 3930}, {"loss": 0.3649, "grad_norm": 0.7315713167190552, "learning_rate": 0.0002, "epoch": 4.84029484029484, "step": 3940}, {"loss": 0.3879, "grad_norm": 0.8924923539161682, "learning_rate": 0.0002, "epoch": 4.8525798525798525, "step": 3950}, {"loss": 0.3669, "grad_norm": 0.9730218052864075, "learning_rate": 0.0002, "epoch": 4.864864864864865, "step": 3960}, {"loss": 0.3705, "grad_norm": 0.9202003479003906, "learning_rate": 0.0002, "epoch": 4.877149877149877, "step": 3970}, {"loss": 0.3617, "grad_norm": 0.8173081874847412, "learning_rate": 0.0002, "epoch": 4.88943488943489, "step": 3980}, {"loss": 0.37, "grad_norm": 0.7178564667701721, "learning_rate": 0.0002, "epoch": 4.901719901719901, "step": 3990}, {"loss": 0.3768, "grad_norm": 0.913684606552124, "learning_rate": 0.0002, "epoch": 4.914004914004914, "step": 4000}, {"loss": 0.3755, "grad_norm": 0.8817896842956543, "learning_rate": 0.0002, "epoch": 4.926289926289926, "step": 4010}, {"loss": 0.3676, "grad_norm": 0.7652186751365662, "learning_rate": 0.0002, "epoch": 4.938574938574939, "step": 4020}, {"loss": 0.3699, "grad_norm": 0.8828630447387695, "learning_rate": 0.0002, "epoch": 4.950859950859951, "step": 4030}, {"loss": 0.3672, "grad_norm": 1.0878605842590332, "learning_rate": 0.0002, "epoch": 4.963144963144963, "step": 4040}, {"loss": 0.3656, "grad_norm": 1.0845288038253784, "learning_rate": 0.0002, "epoch": 4.975429975429975, "step": 4050}, {"loss": 0.365, "grad_norm": 0.8431115746498108, "learning_rate": 0.0002, "epoch": 4.987714987714988, "step": 4060}, {"loss": 0.3693, "grad_norm": 0.8320387601852417, "learning_rate": 0.0002, "epoch": 5.0, "step": 4070}, {"eval_loss": 0.4017423093318939, "eval_runtime": 20.8466, "eval_samples_per_second": 15.878, "eval_steps_per_second": 2.015, "epoch": 5.0, "step": 4070}, {"loss": 0.3425, "grad_norm": 0.8639023900032043, "learning_rate": 0.0002, "epoch": 5.012285012285012, "step": 4080}, {"loss": 0.3458, "grad_norm": 0.7123713493347168, "learning_rate": 0.0002, "epoch": 5.024570024570025, "step": 4090}, {"loss": 0.3404, "grad_norm": 0.9886922836303711, "learning_rate": 0.0002, "epoch": 5.036855036855036, "step": 4100}, {"loss": 0.3529, "grad_norm": 0.7880306243896484, "learning_rate": 0.0002, "epoch": 5.049140049140049, "step": 4110}, {"loss": 0.3406, "grad_norm": 0.7488741874694824, "learning_rate": 0.0002, "epoch": 5.061425061425061, "step": 4120}, {"loss": 0.3542, "grad_norm": 0.9359086751937866, "learning_rate": 0.0002, "epoch": 5.073710073710074, "step": 4130}, {"loss": 0.3471, "grad_norm": 0.9401527047157288, "learning_rate": 0.0002, "epoch": 5.085995085995086, "step": 4140}, {"loss": 0.3566, "grad_norm": 0.8396275043487549, "learning_rate": 0.0002, "epoch": 5.098280098280099, "step": 4150}, {"loss": 0.3416, "grad_norm": 0.7132664918899536, "learning_rate": 0.0002, "epoch": 5.11056511056511, "step": 4160}, {"loss": 0.3457, "grad_norm": 0.843708872795105, "learning_rate": 0.0002, "epoch": 5.122850122850123, "step": 4170}, {"loss": 0.3399, "grad_norm": 0.8733304738998413, "learning_rate": 0.0002, "epoch": 5.135135135135135, "step": 4180}, {"loss": 0.3501, "grad_norm": 0.9064375162124634, "learning_rate": 0.0002, "epoch": 5.1474201474201475, "step": 4190}, {"loss": 0.3455, "grad_norm": 0.900770902633667, "learning_rate": 0.0002, "epoch": 5.15970515970516, "step": 4200}, {"loss": 0.3475, "grad_norm": 0.863853394985199, "learning_rate": 0.0002, "epoch": 5.171990171990172, "step": 4210}, {"loss": 0.3497, "grad_norm": 0.767134964466095, "learning_rate": 0.0002, "epoch": 5.184275184275184, "step": 4220}, {"loss": 0.3527, "grad_norm": 0.7518735527992249, "learning_rate": 0.0002, "epoch": 5.196560196560196, "step": 4230}, {"loss": 0.3369, "grad_norm": 0.8040947914123535, "learning_rate": 0.0002, "epoch": 5.208845208845209, "step": 4240}, {"loss": 0.3496, "grad_norm": 0.7827144265174866, "learning_rate": 0.0002, "epoch": 5.221130221130221, "step": 4250}, {"loss": 0.3442, "grad_norm": 0.7306333184242249, "learning_rate": 0.0002, "epoch": 5.233415233415234, "step": 4260}, {"loss": 0.3553, "grad_norm": 1.0963380336761475, "learning_rate": 0.0002, "epoch": 5.245700245700245, "step": 4270}, {"loss": 0.3462, "grad_norm": 0.8200454711914062, "learning_rate": 0.0002, "epoch": 5.257985257985258, "step": 4280}, {"loss": 0.3509, "grad_norm": 0.8666796684265137, "learning_rate": 0.0002, "epoch": 5.27027027027027, "step": 4290}, {"loss": 0.3423, "grad_norm": 0.7862894535064697, "learning_rate": 0.0002, "epoch": 5.282555282555283, "step": 4300}, {"loss": 0.3623, "grad_norm": 0.8163095712661743, "learning_rate": 0.0002, "epoch": 5.294840294840295, "step": 4310}, {"loss": 0.34, "grad_norm": 0.8069050908088684, "learning_rate": 0.0002, "epoch": 5.3071253071253075, "step": 4320}, {"loss": 0.3532, "grad_norm": 0.7858486175537109, "learning_rate": 0.0002, "epoch": 5.319410319410319, "step": 4330}, {"loss": 0.3435, "grad_norm": 0.950339674949646, "learning_rate": 0.0002, "epoch": 5.3316953316953315, "step": 4340}, {"loss": 0.3498, "grad_norm": 0.9056477546691895, "learning_rate": 0.0002, "epoch": 5.343980343980344, "step": 4350}, {"loss": 0.3538, "grad_norm": 0.9619399905204773, "learning_rate": 0.0002, "epoch": 5.356265356265356, "step": 4360}, {"loss": 0.3455, "grad_norm": 0.9778652191162109, "learning_rate": 0.0002, "epoch": 5.368550368550369, "step": 4370}, {"loss": 0.3498, "grad_norm": 0.6919555068016052, "learning_rate": 0.0002, "epoch": 5.38083538083538, "step": 4380}, {"loss": 0.3426, "grad_norm": 0.8121668696403503, "learning_rate": 0.0002, "epoch": 5.393120393120393, "step": 4390}, {"loss": 0.3442, "grad_norm": 0.8481289148330688, "learning_rate": 0.0002, "epoch": 5.405405405405405, "step": 4400}, {"loss": 0.345, "grad_norm": 0.8727408647537231, "learning_rate": 0.0002, "epoch": 5.417690417690418, "step": 4410}, {"loss": 0.3554, "grad_norm": 0.8920271396636963, "learning_rate": 0.0002, "epoch": 5.42997542997543, "step": 4420}, {"loss": 0.3409, "grad_norm": 0.7758749723434448, "learning_rate": 0.0002, "epoch": 5.442260442260443, "step": 4430}, {"loss": 0.3483, "grad_norm": 0.8847506642341614, "learning_rate": 0.0002, "epoch": 5.454545454545454, "step": 4440}, {"loss": 0.3557, "grad_norm": 0.9760470390319824, "learning_rate": 0.0002, "epoch": 5.466830466830467, "step": 4450}, {"loss": 0.3536, "grad_norm": 0.8940271139144897, "learning_rate": 0.0002, "epoch": 5.479115479115479, "step": 4460}, {"loss": 0.3577, "grad_norm": 0.8668502569198608, "learning_rate": 0.0002, "epoch": 5.4914004914004915, "step": 4470}, {"loss": 0.3462, "grad_norm": 0.9097439050674438, "learning_rate": 0.0002, "epoch": 5.503685503685504, "step": 4480}, {"loss": 0.3417, "grad_norm": 0.8217208981513977, "learning_rate": 0.0002, "epoch": 5.515970515970516, "step": 4490}, {"loss": 0.3482, "grad_norm": 0.7853189706802368, "learning_rate": 0.0002, "epoch": 5.528255528255528, "step": 4500}, {"loss": 0.3479, "grad_norm": 1.1113477945327759, "learning_rate": 0.0002, "epoch": 5.54054054054054, "step": 4510}, {"loss": 0.3553, "grad_norm": 0.8637538552284241, "learning_rate": 0.0002, "epoch": 5.552825552825553, "step": 4520}, {"loss": 0.3403, "grad_norm": 1.0230066776275635, "learning_rate": 0.0002, "epoch": 5.565110565110565, "step": 4530}, {"loss": 0.3588, "grad_norm": 0.8972793817520142, "learning_rate": 0.0002, "epoch": 5.577395577395578, "step": 4540}, {"loss": 0.3428, "grad_norm": 0.7950642704963684, "learning_rate": 0.0002, "epoch": 5.58968058968059, "step": 4550}, {"loss": 0.3468, "grad_norm": 1.113753318786621, "learning_rate": 0.0002, "epoch": 5.601965601965602, "step": 4560}, {"loss": 0.3354, "grad_norm": 0.7842669486999512, "learning_rate": 0.0002, "epoch": 5.614250614250614, "step": 4570}, {"loss": 0.3419, "grad_norm": 0.9713512063026428, "learning_rate": 0.0002, "epoch": 5.6265356265356266, "step": 4580}, {"loss": 0.3502, "grad_norm": 0.9451650977134705, "learning_rate": 0.0002, "epoch": 5.638820638820639, "step": 4590}, {"loss": 0.3416, "grad_norm": 1.055484414100647, "learning_rate": 0.0002, "epoch": 5.651105651105651, "step": 4600}, {"loss": 0.3436, "grad_norm": 0.8408507704734802, "learning_rate": 0.0002, "epoch": 5.663390663390663, "step": 4610}, {"loss": 0.3619, "grad_norm": 1.0293926000595093, "learning_rate": 0.0002, "epoch": 5.675675675675675, "step": 4620}, {"loss": 0.3484, "grad_norm": 0.7198245525360107, "learning_rate": 0.0002, "epoch": 5.687960687960688, "step": 4630}, {"loss": 0.3563, "grad_norm": 0.7564466595649719, "learning_rate": 0.0002, "epoch": 5.7002457002457, "step": 4640}, {"loss": 0.3435, "grad_norm": 0.7980002760887146, "learning_rate": 0.0002, "epoch": 5.712530712530713, "step": 4650}, {"loss": 0.3478, "grad_norm": 0.8685088753700256, "learning_rate": 0.0002, "epoch": 5.724815724815725, "step": 4660}, {"loss": 0.3692, "grad_norm": 0.8816949129104614, "learning_rate": 0.0002, "epoch": 5.737100737100737, "step": 4670}, {"loss": 0.3462, "grad_norm": 0.7154731750488281, "learning_rate": 0.0002, "epoch": 5.749385749385749, "step": 4680}, {"loss": 0.3503, "grad_norm": 0.9430679678916931, "learning_rate": 0.0002, "epoch": 5.761670761670762, "step": 4690}, {"loss": 0.3439, "grad_norm": 0.7640151381492615, "learning_rate": 0.0002, "epoch": 5.773955773955774, "step": 4700}, {"loss": 0.3444, "grad_norm": 1.0920690298080444, "learning_rate": 0.0002, "epoch": 5.7862407862407865, "step": 4710}, {"loss": 0.3356, "grad_norm": 0.9362104535102844, "learning_rate": 0.0002, "epoch": 5.798525798525798, "step": 4720}, {"loss": 0.339, "grad_norm": 0.8392294645309448, "learning_rate": 0.0002, "epoch": 5.8108108108108105, "step": 4730}, {"loss": 0.3488, "grad_norm": 0.9893582463264465, "learning_rate": 0.0002, "epoch": 5.823095823095823, "step": 4740}, {"loss": 0.3446, "grad_norm": 0.6985510587692261, "learning_rate": 0.0002, "epoch": 5.835380835380835, "step": 4750}, {"loss": 0.3534, "grad_norm": 0.8906862735748291, "learning_rate": 0.0002, "epoch": 5.847665847665848, "step": 4760}, {"loss": 0.3481, "grad_norm": 0.8036413192749023, "learning_rate": 0.0002, "epoch": 5.85995085995086, "step": 4770}, {"loss": 0.3326, "grad_norm": 0.9948155283927917, "learning_rate": 0.0002, "epoch": 5.872235872235873, "step": 4780}, {"loss": 0.3385, "grad_norm": 0.8618432283401489, "learning_rate": 0.0002, "epoch": 5.884520884520884, "step": 4790}, {"loss": 0.3302, "grad_norm": 1.0422909259796143, "learning_rate": 0.0002, "epoch": 5.896805896805897, "step": 4800}, {"loss": 0.3448, "grad_norm": 1.1892569065093994, "learning_rate": 0.0002, "epoch": 5.909090909090909, "step": 4810}, {"loss": 0.3506, "grad_norm": 1.1459916830062866, "learning_rate": 0.0002, "epoch": 5.921375921375922, "step": 4820}, {"loss": 0.3387, "grad_norm": 1.056235909461975, "learning_rate": 0.0002, "epoch": 5.933660933660933, "step": 4830}, {"loss": 0.344, "grad_norm": 0.8517277240753174, "learning_rate": 0.0002, "epoch": 5.945945945945946, "step": 4840}, {"loss": 0.3421, "grad_norm": 0.8153380751609802, "learning_rate": 0.0002, "epoch": 5.958230958230958, "step": 4850}, {"loss": 0.3409, "grad_norm": 0.7907533049583435, "learning_rate": 0.0002, "epoch": 5.9705159705159705, "step": 4860}, {"loss": 0.3337, "grad_norm": 0.8443069458007812, "learning_rate": 0.0002, "epoch": 5.982800982800983, "step": 4870}, {"loss": 0.3351, "grad_norm": 0.8711344003677368, "learning_rate": 0.0002, "epoch": 5.995085995085995, "step": 4880}, {"eval_loss": 0.3778059184551239, "eval_runtime": 20.6858, "eval_samples_per_second": 16.001, "eval_steps_per_second": 2.03, "epoch": 6.0, "step": 4884}, {"loss": 0.3244, "grad_norm": 0.7697948813438416, "learning_rate": 0.0002, "epoch": 6.007371007371007, "step": 4890}, {"loss": 0.3118, "grad_norm": 0.7734108567237854, "learning_rate": 0.0002, "epoch": 6.019656019656019, "step": 4900}, {"loss": 0.3242, "grad_norm": 0.7173922657966614, "learning_rate": 0.0002, "epoch": 6.031941031941032, "step": 4910}, {"loss": 0.3159, "grad_norm": 1.062118649482727, "learning_rate": 0.0002, "epoch": 6.044226044226044, "step": 4920}, {"loss": 0.3361, "grad_norm": 0.746422529220581, "learning_rate": 0.0002, "epoch": 6.056511056511057, "step": 4930}, {"loss": 0.3204, "grad_norm": 0.8549448251724243, "learning_rate": 0.0002, "epoch": 6.068796068796069, "step": 4940}, {"loss": 0.3236, "grad_norm": 0.9405432939529419, "learning_rate": 0.0002, "epoch": 6.081081081081081, "step": 4950}, {"loss": 0.3278, "grad_norm": 0.752382755279541, "learning_rate": 0.0002, "epoch": 6.093366093366093, "step": 4960}, {"loss": 0.3204, "grad_norm": 0.820332407951355, "learning_rate": 0.0002, "epoch": 6.105651105651106, "step": 4970}, {"loss": 0.3192, "grad_norm": 0.8701449036598206, "learning_rate": 0.0002, "epoch": 6.117936117936118, "step": 4980}, {"loss": 0.321, "grad_norm": 0.8192865252494812, "learning_rate": 0.0002, "epoch": 6.1302211302211305, "step": 4990}, {"loss": 0.3295, "grad_norm": 1.0016303062438965, "learning_rate": 0.0002, "epoch": 6.142506142506143, "step": 5000}, {"loss": 0.3352, "grad_norm": 0.9194409251213074, "learning_rate": 0.0002, "epoch": 6.1547911547911545, "step": 5010}, {"loss": 0.3205, "grad_norm": 0.9319757223129272, "learning_rate": 0.0002, "epoch": 6.167076167076167, "step": 5020}, {"loss": 0.3256, "grad_norm": 0.8737656474113464, "learning_rate": 0.0002, "epoch": 6.179361179361179, "step": 5030}, {"loss": 0.3221, "grad_norm": 0.8736537098884583, "learning_rate": 0.0002, "epoch": 6.191646191646192, "step": 5040}, {"loss": 0.3265, "grad_norm": 0.9301430583000183, "learning_rate": 0.0002, "epoch": 6.203931203931204, "step": 5050}, {"loss": 0.3285, "grad_norm": 0.7717130780220032, "learning_rate": 0.0002, "epoch": 6.216216216216216, "step": 5060}, {"loss": 0.3192, "grad_norm": 0.6709604859352112, "learning_rate": 0.0002, "epoch": 6.228501228501228, "step": 5070}, {"loss": 0.3352, "grad_norm": 0.879374086856842, "learning_rate": 0.0002, "epoch": 6.240786240786241, "step": 5080}, {"loss": 0.329, "grad_norm": 0.9136955738067627, "learning_rate": 0.0002, "epoch": 6.253071253071253, "step": 5090}, {"loss": 0.3228, "grad_norm": 0.795177161693573, "learning_rate": 0.0002, "epoch": 6.2653562653562656, "step": 5100}, {"loss": 0.3273, "grad_norm": 1.0412259101867676, "learning_rate": 0.0002, "epoch": 6.277641277641278, "step": 5110}, {"loss": 0.3221, "grad_norm": 0.7382524013519287, "learning_rate": 0.0002, "epoch": 6.2899262899262895, "step": 5120}, {"loss": 0.3102, "grad_norm": 0.8818480968475342, "learning_rate": 0.0002, "epoch": 6.302211302211302, "step": 5130}, {"loss": 0.3316, "grad_norm": 0.7865153551101685, "learning_rate": 0.0002, "epoch": 6.314496314496314, "step": 5140}, {"loss": 0.3264, "grad_norm": 0.9166486859321594, "learning_rate": 0.0002, "epoch": 6.326781326781327, "step": 5150}, {"loss": 0.33, "grad_norm": 0.6655149459838867, "learning_rate": 0.0002, "epoch": 6.339066339066339, "step": 5160}, {"loss": 0.3359, "grad_norm": 0.7762818336486816, "learning_rate": 0.0002, "epoch": 6.351351351351352, "step": 5170}, {"loss": 0.3244, "grad_norm": 0.8057235479354858, "learning_rate": 0.0002, "epoch": 6.363636363636363, "step": 5180}, {"loss": 0.3167, "grad_norm": 0.8186984062194824, "learning_rate": 0.0002, "epoch": 6.375921375921376, "step": 5190}, {"loss": 0.3289, "grad_norm": 0.8669573068618774, "learning_rate": 0.0002, "epoch": 6.388206388206388, "step": 5200}, {"loss": 0.3313, "grad_norm": 0.8904402852058411, "learning_rate": 0.0002, "epoch": 6.400491400491401, "step": 5210}, {"loss": 0.3187, "grad_norm": 0.9250359535217285, "learning_rate": 0.0002, "epoch": 6.412776412776413, "step": 5220}, {"loss": 0.3229, "grad_norm": 0.8718299269676208, "learning_rate": 0.0002, "epoch": 6.4250614250614255, "step": 5230}, {"loss": 0.3214, "grad_norm": 0.8156430125236511, "learning_rate": 0.0002, "epoch": 6.437346437346437, "step": 5240}, {"loss": 0.3244, "grad_norm": 0.7759218215942383, "learning_rate": 0.0002, "epoch": 6.4496314496314495, "step": 5250}, {"loss": 0.3298, "grad_norm": 0.8137310743331909, "learning_rate": 0.0002, "epoch": 6.461916461916462, "step": 5260}, {"loss": 0.3275, "grad_norm": 0.8121917843818665, "learning_rate": 0.0002, "epoch": 6.474201474201474, "step": 5270}, {"loss": 0.3201, "grad_norm": 0.8178010582923889, "learning_rate": 0.0002, "epoch": 6.486486486486487, "step": 5280}, {"loss": 0.3271, "grad_norm": 1.1806302070617676, "learning_rate": 0.0002, "epoch": 6.498771498771498, "step": 5290}, {"loss": 0.3231, "grad_norm": 0.8255127668380737, "learning_rate": 0.0002, "epoch": 6.511056511056511, "step": 5300}, {"loss": 0.3227, "grad_norm": 0.8006690740585327, "learning_rate": 0.0002, "epoch": 6.523341523341523, "step": 5310}, {"loss": 0.3262, "grad_norm": 0.9932374358177185, "learning_rate": 0.0002, "epoch": 6.535626535626536, "step": 5320}, {"loss": 0.3291, "grad_norm": 0.8973969221115112, "learning_rate": 0.0002, "epoch": 6.547911547911548, "step": 5330}, {"loss": 0.3146, "grad_norm": 0.7359915971755981, "learning_rate": 0.0002, "epoch": 6.560196560196561, "step": 5340}, {"loss": 0.3308, "grad_norm": 0.9941133856773376, "learning_rate": 0.0002, "epoch": 6.572481572481572, "step": 5350}, {"loss": 0.3202, "grad_norm": 0.9008874893188477, "learning_rate": 0.0002, "epoch": 6.584766584766585, "step": 5360}, {"loss": 0.3271, "grad_norm": 1.309710144996643, "learning_rate": 0.0002, "epoch": 6.597051597051597, "step": 5370}, {"loss": 0.3177, "grad_norm": 0.797768235206604, "learning_rate": 0.0002, "epoch": 6.6093366093366095, "step": 5380}, {"loss": 0.3218, "grad_norm": 0.8507353663444519, "learning_rate": 0.0002, "epoch": 6.621621621621622, "step": 5390}, {"loss": 0.3204, "grad_norm": 0.9628674983978271, "learning_rate": 0.0002, "epoch": 6.6339066339066335, "step": 5400}, {"loss": 0.3155, "grad_norm": 0.6989983320236206, "learning_rate": 0.0002, "epoch": 6.646191646191646, "step": 5410}, {"loss": 0.3197, "grad_norm": 0.9505863189697266, "learning_rate": 0.0002, "epoch": 6.658476658476658, "step": 5420}, {"loss": 0.3259, "grad_norm": 0.8058171272277832, "learning_rate": 0.0002, "epoch": 6.670761670761671, "step": 5430}, {"loss": 0.3248, "grad_norm": 0.8476499915122986, "learning_rate": 0.0002, "epoch": 6.683046683046683, "step": 5440}, {"loss": 0.326, "grad_norm": 0.8503309488296509, "learning_rate": 0.0002, "epoch": 6.695331695331696, "step": 5450}, {"loss": 0.3218, "grad_norm": 0.919566810131073, "learning_rate": 0.0002, "epoch": 6.707616707616707, "step": 5460}, {"loss": 0.3218, "grad_norm": 0.7741201519966125, "learning_rate": 0.0002, "epoch": 6.71990171990172, "step": 5470}, {"loss": 0.329, "grad_norm": 0.8432701826095581, "learning_rate": 0.0002, "epoch": 6.732186732186732, "step": 5480}, {"loss": 0.3284, "grad_norm": 1.0183148384094238, "learning_rate": 0.0002, "epoch": 6.744471744471745, "step": 5490}, {"loss": 0.3312, "grad_norm": 0.8491143584251404, "learning_rate": 0.0002, "epoch": 6.756756756756757, "step": 5500}, {"loss": 0.3208, "grad_norm": 0.9586310386657715, "learning_rate": 0.0002, "epoch": 6.769041769041769, "step": 5510}, {"loss": 0.3305, "grad_norm": 0.7936097383499146, "learning_rate": 0.0002, "epoch": 6.781326781326781, "step": 5520}, {"loss": 0.318, "grad_norm": 0.7875059247016907, "learning_rate": 0.0002, "epoch": 6.7936117936117935, "step": 5530}, {"loss": 0.3234, "grad_norm": 0.8136157393455505, "learning_rate": 0.0002, "epoch": 6.805896805896806, "step": 5540}, {"loss": 0.3161, "grad_norm": 0.837213933467865, "learning_rate": 0.0002, "epoch": 6.818181818181818, "step": 5550}, {"loss": 0.3153, "grad_norm": 0.6812925338745117, "learning_rate": 0.0002, "epoch": 6.830466830466831, "step": 5560}, {"loss": 0.3139, "grad_norm": 0.7309592962265015, "learning_rate": 0.0002, "epoch": 6.842751842751843, "step": 5570}, {"loss": 0.3126, "grad_norm": 0.6905979514122009, "learning_rate": 0.0002, "epoch": 6.855036855036855, "step": 5580}, {"loss": 0.3291, "grad_norm": 1.1768406629562378, "learning_rate": 0.0002, "epoch": 6.867321867321867, "step": 5590}, {"loss": 0.3193, "grad_norm": 0.7618567943572998, "learning_rate": 0.0002, "epoch": 6.87960687960688, "step": 5600}, {"loss": 0.3296, "grad_norm": 0.7930929660797119, "learning_rate": 0.0002, "epoch": 6.891891891891892, "step": 5610}, {"loss": 0.3241, "grad_norm": 0.7931787371635437, "learning_rate": 0.0002, "epoch": 6.9041769041769046, "step": 5620}, {"loss": 0.3215, "grad_norm": 0.6366972923278809, "learning_rate": 0.0002, "epoch": 6.916461916461916, "step": 5630}, {"loss": 0.3264, "grad_norm": 0.7782737612724304, "learning_rate": 0.0002, "epoch": 6.9287469287469285, "step": 5640}, {"loss": 0.3186, "grad_norm": 0.8643787503242493, "learning_rate": 0.0002, "epoch": 6.941031941031941, "step": 5650}, {"loss": 0.3285, "grad_norm": 1.0843733549118042, "learning_rate": 0.0002, "epoch": 6.953316953316953, "step": 5660}, {"loss": 0.3163, "grad_norm": 0.71319180727005, "learning_rate": 0.0002, "epoch": 6.965601965601966, "step": 5670}, {"loss": 0.3196, "grad_norm": 0.976536750793457, "learning_rate": 0.0002, "epoch": 6.977886977886978, "step": 5680}, {"loss": 0.3255, "grad_norm": 0.9221968054771423, "learning_rate": 0.0002, "epoch": 6.99017199017199, "step": 5690}, {"eval_loss": 0.3616626560688019, "eval_runtime": 20.8747, "eval_samples_per_second": 15.857, "eval_steps_per_second": 2.012, "epoch": 7.0, "step": 5698}, {"loss": 0.3149, "grad_norm": 0.6302434802055359, "learning_rate": 0.0002, "epoch": 7.002457002457002, "step": 5700}, {"loss": 0.3017, "grad_norm": 0.7077583074569702, "learning_rate": 0.0002, "epoch": 7.014742014742015, "step": 5710}, {"loss": 0.303, "grad_norm": 0.7005309462547302, "learning_rate": 0.0002, "epoch": 7.027027027027027, "step": 5720}, {"loss": 0.3069, "grad_norm": 0.7724815607070923, "learning_rate": 0.0002, "epoch": 7.03931203931204, "step": 5730}, {"loss": 0.3002, "grad_norm": 0.6469350457191467, "learning_rate": 0.0002, "epoch": 7.051597051597051, "step": 5740}, {"loss": 0.3046, "grad_norm": 0.8406739234924316, "learning_rate": 0.0002, "epoch": 7.063882063882064, "step": 5750}, {"loss": 0.3108, "grad_norm": 0.9954310059547424, "learning_rate": 0.0002, "epoch": 7.076167076167076, "step": 5760}, {"loss": 0.3076, "grad_norm": 0.7063487768173218, "learning_rate": 0.0002, "epoch": 7.0884520884520885, "step": 5770}, {"loss": 0.3033, "grad_norm": 0.8696660995483398, "learning_rate": 0.0002, "epoch": 7.100737100737101, "step": 5780}, {"loss": 0.3049, "grad_norm": 0.8088991045951843, "learning_rate": 0.0002, "epoch": 7.113022113022113, "step": 5790}, {"loss": 0.3042, "grad_norm": 0.6934662461280823, "learning_rate": 0.0002, "epoch": 7.125307125307125, "step": 5800}, {"loss": 0.3068, "grad_norm": 0.7482573390007019, "learning_rate": 0.0002, "epoch": 7.137592137592137, "step": 5810}, {"loss": 0.3001, "grad_norm": 1.0848287343978882, "learning_rate": 0.0002, "epoch": 7.14987714987715, "step": 5820}, {"loss": 0.3017, "grad_norm": 0.8017896413803101, "learning_rate": 0.0002, "epoch": 7.162162162162162, "step": 5830}, {"loss": 0.3051, "grad_norm": 0.6418949365615845, "learning_rate": 0.0002, "epoch": 7.174447174447175, "step": 5840}, {"loss": 0.3032, "grad_norm": 0.666072428226471, "learning_rate": 0.0002, "epoch": 7.186732186732186, "step": 5850}, {"loss": 0.3131, "grad_norm": 0.7549816370010376, "learning_rate": 0.0002, "epoch": 7.199017199017199, "step": 5860}, {"loss": 0.3088, "grad_norm": 0.8756735920906067, "learning_rate": 0.0002, "epoch": 7.211302211302211, "step": 5870}, {"loss": 0.3022, "grad_norm": 0.6790788769721985, "learning_rate": 0.0002, "epoch": 7.223587223587224, "step": 5880}, {"loss": 0.3011, "grad_norm": 0.8388362526893616, "learning_rate": 0.0002, "epoch": 7.235872235872236, "step": 5890}, {"loss": 0.3204, "grad_norm": 0.8915345668792725, "learning_rate": 0.0002, "epoch": 7.2481572481572485, "step": 5900}, {"loss": 0.3086, "grad_norm": 0.9234250783920288, "learning_rate": 0.0002, "epoch": 7.26044226044226, "step": 5910}, {"loss": 0.2981, "grad_norm": 0.5452191233634949, "learning_rate": 0.0002, "epoch": 7.2727272727272725, "step": 5920}, {"loss": 0.3054, "grad_norm": 0.6100478172302246, "learning_rate": 0.0002, "epoch": 7.285012285012285, "step": 5930}, {"loss": 0.3073, "grad_norm": 0.6258270740509033, "learning_rate": 0.0002, "epoch": 7.297297297297297, "step": 5940}, {"loss": 0.3179, "grad_norm": 0.8540555834770203, "learning_rate": 0.0002, "epoch": 7.30958230958231, "step": 5950}, {"loss": 0.3109, "grad_norm": 0.8662564754486084, "learning_rate": 0.0002, "epoch": 7.321867321867322, "step": 5960}, {"loss": 0.3039, "grad_norm": 0.7404284477233887, "learning_rate": 0.0002, "epoch": 7.334152334152334, "step": 5970}, {"loss": 0.3036, "grad_norm": 0.7579419612884521, "learning_rate": 0.0002, "epoch": 7.346437346437346, "step": 5980}, {"loss": 0.3113, "grad_norm": 0.7248510122299194, "learning_rate": 0.0002, "epoch": 7.358722358722359, "step": 5990}, {"loss": 0.2987, "grad_norm": 0.8882181644439697, "learning_rate": 0.0002, "epoch": 7.371007371007371, "step": 6000}, {"loss": 0.3026, "grad_norm": 0.8494889736175537, "learning_rate": 0.0002, "epoch": 7.383292383292384, "step": 6010}, {"loss": 0.3147, "grad_norm": 0.8501948118209839, "learning_rate": 0.0002, "epoch": 7.395577395577396, "step": 6020}, {"loss": 0.3122, "grad_norm": 0.7228043079376221, "learning_rate": 0.0002, "epoch": 7.407862407862408, "step": 6030}, {"loss": 0.3092, "grad_norm": 0.7471523284912109, "learning_rate": 0.0002, "epoch": 7.42014742014742, "step": 6040}, {"loss": 0.307, "grad_norm": 0.810962975025177, "learning_rate": 0.0002, "epoch": 7.4324324324324325, "step": 6050}, {"loss": 0.3024, "grad_norm": 1.0621764659881592, "learning_rate": 0.0002, "epoch": 7.444717444717445, "step": 6060}, {"loss": 0.3019, "grad_norm": 0.72637939453125, "learning_rate": 0.0002, "epoch": 7.457002457002457, "step": 6070}, {"loss": 0.314, "grad_norm": 1.1550157070159912, "learning_rate": 0.0002, "epoch": 7.469287469287469, "step": 6080}, {"loss": 0.3088, "grad_norm": 0.865250825881958, "learning_rate": 0.0002, "epoch": 7.481572481572481, "step": 6090}, {"loss": 0.3041, "grad_norm": 0.8407077789306641, "learning_rate": 0.0002, "epoch": 7.493857493857494, "step": 6100}, {"loss": 0.3064, "grad_norm": 0.7295752167701721, "learning_rate": 0.0002, "epoch": 7.506142506142506, "step": 6110}, {"loss": 0.3061, "grad_norm": 0.9728897213935852, "learning_rate": 0.0002, "epoch": 7.518427518427519, "step": 6120}, {"loss": 0.3107, "grad_norm": 0.9776952862739563, "learning_rate": 0.0002, "epoch": 7.530712530712531, "step": 6130}, {"loss": 0.3148, "grad_norm": 0.704113245010376, "learning_rate": 0.0002, "epoch": 7.542997542997543, "step": 6140}, {"loss": 0.3012, "grad_norm": 0.9030590057373047, "learning_rate": 0.0002, "epoch": 7.555282555282555, "step": 6150}, {"loss": 0.3134, "grad_norm": 0.6629155874252319, "learning_rate": 0.0002, "epoch": 7.5675675675675675, "step": 6160}, {"loss": 0.3068, "grad_norm": 0.9348171353340149, "learning_rate": 0.0002, "epoch": 7.57985257985258, "step": 6170}, {"loss": 0.3065, "grad_norm": 0.9363399744033813, "learning_rate": 0.0002, "epoch": 7.592137592137592, "step": 6180}, {"loss": 0.3099, "grad_norm": 0.902718186378479, "learning_rate": 0.0002, "epoch": 7.604422604422604, "step": 6190}, {"loss": 0.3082, "grad_norm": 0.6992074251174927, "learning_rate": 0.0002, "epoch": 7.616707616707616, "step": 6200}, {"loss": 0.2941, "grad_norm": 0.7574757933616638, "learning_rate": 0.0002, "epoch": 7.628992628992629, "step": 6210}, {"loss": 0.3079, "grad_norm": 0.7717660069465637, "learning_rate": 0.0002, "epoch": 7.641277641277641, "step": 6220}, {"loss": 0.3005, "grad_norm": 0.7789981961250305, "learning_rate": 0.0002, "epoch": 7.653562653562654, "step": 6230}, {"loss": 0.3112, "grad_norm": 1.1020026206970215, "learning_rate": 0.0002, "epoch": 7.665847665847666, "step": 6240}, {"loss": 0.3087, "grad_norm": 0.7290350794792175, "learning_rate": 0.0002, "epoch": 7.678132678132678, "step": 6250}, {"loss": 0.3023, "grad_norm": 0.7291128039360046, "learning_rate": 0.0002, "epoch": 7.69041769041769, "step": 6260}, {"loss": 0.3019, "grad_norm": 0.7766857147216797, "learning_rate": 0.0002, "epoch": 7.702702702702703, "step": 6270}, {"loss": 0.3039, "grad_norm": 0.938277542591095, "learning_rate": 0.0002, "epoch": 7.714987714987715, "step": 6280}, {"loss": 0.3103, "grad_norm": 0.785190761089325, "learning_rate": 0.0002, "epoch": 7.7272727272727275, "step": 6290}, {"loss": 0.2938, "grad_norm": 0.7140066623687744, "learning_rate": 0.0002, "epoch": 7.739557739557739, "step": 6300}, {"loss": 0.3042, "grad_norm": 0.9476789236068726, "learning_rate": 0.0002, "epoch": 7.7518427518427515, "step": 6310}, {"loss": 0.3035, "grad_norm": 0.6404930949211121, "learning_rate": 0.0002, "epoch": 7.764127764127764, "step": 6320}, {"loss": 0.3065, "grad_norm": 0.6433947682380676, "learning_rate": 0.0002, "epoch": 7.776412776412776, "step": 6330}, {"loss": 0.3117, "grad_norm": 0.8289583921432495, "learning_rate": 0.0002, "epoch": 7.788697788697789, "step": 6340}, {"loss": 0.3057, "grad_norm": 1.098555088043213, "learning_rate": 0.0002, "epoch": 7.800982800982801, "step": 6350}, {"loss": 0.3104, "grad_norm": 0.7225303053855896, "learning_rate": 0.0002, "epoch": 7.813267813267814, "step": 6360}, {"loss": 0.3043, "grad_norm": 0.845711886882782, "learning_rate": 0.0002, "epoch": 7.825552825552825, "step": 6370}, {"loss": 0.3099, "grad_norm": 0.6199421882629395, "learning_rate": 0.0002, "epoch": 7.837837837837838, "step": 6380}, {"loss": 0.3095, "grad_norm": 0.7576995491981506, "learning_rate": 0.0002, "epoch": 7.85012285012285, "step": 6390}, {"loss": 0.311, "grad_norm": 0.6669192314147949, "learning_rate": 0.0002, "epoch": 7.862407862407863, "step": 6400}, {"loss": 0.2953, "grad_norm": 0.6896083354949951, "learning_rate": 0.0002, "epoch": 7.874692874692875, "step": 6410}, {"loss": 0.3, "grad_norm": 0.9418429732322693, "learning_rate": 0.0002, "epoch": 7.886977886977887, "step": 6420}, {"loss": 0.3074, "grad_norm": 0.7120184302330017, "learning_rate": 0.0002, "epoch": 7.899262899262899, "step": 6430}, {"loss": 0.3158, "grad_norm": 0.7420004606246948, "learning_rate": 0.0002, "epoch": 7.9115479115479115, "step": 6440}, {"loss": 0.3068, "grad_norm": 0.8989502191543579, "learning_rate": 0.0002, "epoch": 7.923832923832924, "step": 6450}, {"loss": 0.3102, "grad_norm": 0.715905487537384, "learning_rate": 0.0002, "epoch": 7.936117936117936, "step": 6460}, {"loss": 0.3018, "grad_norm": 0.8890138268470764, "learning_rate": 0.0002, "epoch": 7.948402948402949, "step": 6470}, {"loss": 0.3179, "grad_norm": 0.7992095351219177, "learning_rate": 0.0002, "epoch": 7.96068796068796, "step": 6480}, {"loss": 0.3115, "grad_norm": 0.9169677495956421, "learning_rate": 0.0002, "epoch": 7.972972972972973, "step": 6490}, {"loss": 0.3001, "grad_norm": 0.7911704778671265, "learning_rate": 0.0002, "epoch": 7.985257985257985, "step": 6500}, {"loss": 0.3085, "grad_norm": 0.8787347078323364, "learning_rate": 0.0002, "epoch": 7.997542997542998, "step": 6510}]}