diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..426af4eb6909e3c5e7c1343472d1051a0155f727
Binary files /dev/null and b/.DS_Store differ
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-100/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-100/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a6df65ab7f71ac324ffc87aaebbb8fdf3e5e6df8
--- /dev/null
+++ b/checkpoint-100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189f16e272512604f417acb61041d13ea8cf5491faaf3775a73fa8eb7acfcba9
+size 3695848
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b7a9eaeace23d23fb0876312d6086768bdbb6d42
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7446647508a3f1e193d8002f3abea6912b4f0b6763c7dc576d37e298b2eaf9
+size 7433594
diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16771faa3f088413763e4ed8c5ff3fe5cb439d23
--- /dev/null
+++ b/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b6b7e6cf0b505cf781760539befb21856622708465aec629481b220a020626
+size 14244
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d1b090ccb725bac0f6385b5ebc76d447866e6428
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798d14d73ca2d10bac9b41826264fce38de23cc8ba8f11a956f55eaab401ae24
+size 1064
diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-100/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-100/tokenizer.model b/checkpoint-100/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-100/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-100/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..290af034d0b7672d59c0aeb629bd2c38e117de5a
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,99 @@
+{
+  "best_metric": 2.126384735107422,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-100",
+  "epoch": 0.17777777777777778,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 8.247898064093184e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1000/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1000/adapter_config.json b/checkpoint-1000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1000/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1000/adapter_model.safetensors b/checkpoint-1000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e8fcc3c306544852763bc92d68bbeed6030b9b64
--- /dev/null
+++ b/checkpoint-1000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7916de9ea406d8a03c10557143738d35307ad45987482ebb9e93d9db165ad52
+size 3695848
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d87715c66afd2b4d5f523f9ead37f0ebefd3f745
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd862fdf8905f2cd906d896bfa4adb91e72c8b2a9e37933d9818163f89b1855e
+size 7433594
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d0624c55dbf111a545343527344831df83b9e31a
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e16eaed4b8b35384ad183eb82126dc2f08137ade07d11c29930267932cc1ea1
+size 14244
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0fba7abf5b78ebb770295701b05eb8e07f4c4edb
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53349943fc3bda7b7686dfb1b7835d2ed6729aa6a46db4b4e53d5c6f633658c9
+size 1064
diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1000/tokenizer.model b/checkpoint-1000/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1000/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8f3eb22b0270d8b0d2a2bfcf161b9fc4bf96df87
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,801 @@
+{
+  "best_metric": 1.5386379957199097,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1000",
+  "epoch": 1.7777777777777777,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7.861412473287475e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1100/README.md b/checkpoint-1100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1100/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1100/adapter_config.json b/checkpoint-1100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1100/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1100/adapter_model.safetensors b/checkpoint-1100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..20324857492decc395a1b92e283e21507504c3cf
--- /dev/null
+++ b/checkpoint-1100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b9eb06e71d7973f8a07ec27b6a40c58f903b3a4ba384017bc0f6e2a2196c4b
+size 3695848
diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5d0916b7af282fe5bf99d6607ec06d794b16b7ef
--- /dev/null
+++ b/checkpoint-1100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725db80f8de0a9d1939950241fb60493a3d4a4da625c46af710b20696067ba64
+size 7433594
diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3e25cff94241d1d51da6ec770b900487240d0503
--- /dev/null
+++ b/checkpoint-1100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664509c403435e02712a1f6ee4f0fe06f1cdce5a2a4e368b12808975f9d67973
+size 14244
diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..db156dd70fb7b899a4fe2d7d51de608c3e5f4ced
--- /dev/null
+++ b/checkpoint-1100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf8f94804871a990551a025205f7d78b0c82ddb68268b867708cefdd898eeb3
+size 1064
diff --git a/checkpoint-1100/special_tokens_map.json b/checkpoint-1100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1100/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1100/tokenizer.model b/checkpoint-1100/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1100/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1100/tokenizer_config.json b/checkpoint-1100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1100/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..185d3b92150a992a9f7646349a3b099973f53e06
--- /dev/null
+++ b/checkpoint-1100/trainer_state.json
@@ -0,0 +1,879 @@
+{
+  "best_metric": 1.5198711156845093,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1100",
+  "epoch": 1.9555555555555557,
+  "eval_steps": 100,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 8.600909737867346e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1200/README.md b/checkpoint-1200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1200/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1200/adapter_config.json b/checkpoint-1200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1200/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1200/adapter_model.safetensors b/checkpoint-1200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5ccfea1bcb22bda64943df38e447c45056a8d400
--- /dev/null
+++ b/checkpoint-1200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ffbe8de08fe4d834e15ba4cb1361370d23f5218e15f7836f3f1863cbfd4b84
+size 3695848
diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d4508df3094ed72add16d9163e28df44d9520f2b
--- /dev/null
+++ b/checkpoint-1200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14447e20d16512af5af2f3d5355e9061f5d86b9f45fdd6e3de7f65af2f7e6ec
+size 7433594
diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b31c5601a7f39fdb5f7c7b205ce6b1b838aca11
--- /dev/null
+++ b/checkpoint-1200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7b75b55e4564c8897b2e74676b56608a7a54046d34b7140d36e3fecaa54d17
+size 14244
diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f37fc99403e2438d01888f45bad1610cfbbd6e42
--- /dev/null
+++ b/checkpoint-1200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16774d623c8977b5af4f890ada5f121527f570596390b865e9450991873920b
+size 1064
diff --git a/checkpoint-1200/special_tokens_map.json b/checkpoint-1200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1200/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1200/tokenizer.model b/checkpoint-1200/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1200/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1200/tokenizer_config.json b/checkpoint-1200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1200/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3c97c1c9faee7962f48b3c1bef222f508e11d43
--- /dev/null
+++ b/checkpoint-1200/trainer_state.json
@@ -0,0 +1,957 @@
+{
+  "best_metric": 1.5145190954208374,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1200",
+  "epoch": 2.1333333333333333,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 9.345143605029765e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1300/README.md b/checkpoint-1300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1300/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1300/adapter_config.json b/checkpoint-1300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1300/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1300/adapter_model.safetensors b/checkpoint-1300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..51e366d242f788d8a7fddfa8f75f10c5aaea593a
--- /dev/null
+++ b/checkpoint-1300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd707712dd82358da79a33ee9f1c986f6405353e769651f7ac4db92b2079d77
+size 3695848
diff --git a/checkpoint-1300/optimizer.pt b/checkpoint-1300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..27669f3a0e0681bd0144e201651e338001917032
--- /dev/null
+++ b/checkpoint-1300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71434438c6b8408bde4caf0128d81bbeb25b13b24e638b72f5195085c2e81e47
+size 7433594
diff --git a/checkpoint-1300/rng_state.pth b/checkpoint-1300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..986a56f5712aeaae6e1215bde30448d4d9db638d
--- /dev/null
+++ b/checkpoint-1300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdcb35c24b5daeb5cb101341c361e48eb368eb2034e53248c5f637b582676b7a
+size 14244
diff --git a/checkpoint-1300/scheduler.pt b/checkpoint-1300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..58e58fce20e078ddc45b92aca0c5f670daa19fc5
--- /dev/null
+++ b/checkpoint-1300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c165513408538ccddcaa8244e302fcd0ee9c15713dd0c456621a1c0c3d17aec0
+size 1064
diff --git a/checkpoint-1300/special_tokens_map.json b/checkpoint-1300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1300/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1300/tokenizer.model b/checkpoint-1300/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1300/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1300/tokenizer_config.json b/checkpoint-1300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1300/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1300/trainer_state.json b/checkpoint-1300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a7408217e92c6df9676a753d263b9b0ec6e23469
--- /dev/null
+++ b/checkpoint-1300/trainer_state.json
@@ -0,0 +1,1035 @@
+{
+  "best_metric": 1.504623532295227,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1300",
+  "epoch": 2.311111111111111,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.010572452744659e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1300/training_args.bin b/checkpoint-1300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1400/README.md b/checkpoint-1400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1400/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1400/adapter_config.json b/checkpoint-1400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1400/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1400/adapter_model.safetensors b/checkpoint-1400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..13827582981f91b9d2fe89ec1543a804cae9f5d2
--- /dev/null
+++ b/checkpoint-1400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c214b62247a52aa4942afe49e726bbfffc8ef04f492c747323bcbdb317f0aa
+size 3695848
diff --git a/checkpoint-1400/optimizer.pt b/checkpoint-1400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b587a86066aa9819b46081fb6bc9aa6bbcdbd682
--- /dev/null
+++ b/checkpoint-1400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f948275636df9d282451ca91bcb81adf0ae49ad0a8ca11735782fbbc7b5447b2
+size 7433594
diff --git a/checkpoint-1400/rng_state.pth b/checkpoint-1400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cfd4c8122f37f963437cdd7519832c075f8941b6
--- /dev/null
+++ b/checkpoint-1400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9248879f882b1ddec0c0bf83dda9481bdf345a65bb26a9a0ca7a4fad7a6a52d
+size 14244
diff --git a/checkpoint-1400/scheduler.pt b/checkpoint-1400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..417c8f49d2aad3440f71c484bde6bef44d208d45
--- /dev/null
+++ b/checkpoint-1400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd20179f117c92cee3e8119d3f69bc4babcc8c74f8384e502c07940a1e5b1528
+size 1064
diff --git a/checkpoint-1400/special_tokens_map.json b/checkpoint-1400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1400/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1400/tokenizer.model b/checkpoint-1400/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1400/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1400/tokenizer_config.json b/checkpoint-1400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1400/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1400/trainer_state.json b/checkpoint-1400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..da0258aacb9b11024abf033834468ba0ca431608
--- /dev/null
+++ b/checkpoint-1400/trainer_state.json
@@ -0,0 +1,1113 @@
+{
+  "best_metric": 1.498180627822876,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1400",
+  "epoch": 2.488888888888889,
+  "eval_steps": 100,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.0866907152427254e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1400/training_args.bin b/checkpoint-1400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1500/README.md b/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1500/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_config.json b/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1500/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1500/adapter_model.safetensors b/checkpoint-1500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c58f92f9282867083740399e2cb04690e77a4152
--- /dev/null
+++ b/checkpoint-1500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29f3e1f1182e346950cbf796e51d4023338b936e020e1970ef13e67ae30cc8a
+size 3695848
diff --git a/checkpoint-1500/optimizer.pt b/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c48e3d2840af32965852b4f58b06f5c2403ed0d6
--- /dev/null
+++ b/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6ccf96b1459f5d6795b645817dc45059dfb077f42b2acdceaa20b0b67be88b
+size 7433594
diff --git a/checkpoint-1500/rng_state.pth b/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..54688aa49f444f096ca34a005ad8ae3326bc2187
--- /dev/null
+++ b/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7e6f6110044ba16125efcc10e09e6a75d8e8e1308c4939cf51fddad6624a54
+size 14244
diff --git a/checkpoint-1500/scheduler.pt b/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..020d2165b03e9c8f7dda028e8bf3f6dbdfe953cf
--- /dev/null
+++ b/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16d14b00a11f0ce9fda4d09d4f83450cf1a6468eea32573e43c47e34aed9fbc
+size 1064
diff --git a/checkpoint-1500/special_tokens_map.json b/checkpoint-1500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1500/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1500/tokenizer.model b/checkpoint-1500/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1500/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1500/tokenizer_config.json b/checkpoint-1500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1500/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1500/trainer_state.json b/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a268aa501066666d6297378a45c8bfc62c7ba75c
--- /dev/null
+++ b/checkpoint-1500/trainer_state.json
@@ -0,0 +1,1191 @@
+{
+  "best_metric": 1.498180627822876,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1400",
+  "epoch": 2.6666666666666665,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.1665294250335273e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1500/training_args.bin b/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1600/README.md b/checkpoint-1600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1600/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1600/adapter_config.json b/checkpoint-1600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1600/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1600/adapter_model.safetensors b/checkpoint-1600/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..60307a4282c6ac66b63e79b42dbf951f751952db
--- /dev/null
+++ b/checkpoint-1600/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5997cd1e1ccec7645a35d86f8fb3e685494291279d220450fde774953970c028
+size 3695848
diff --git a/checkpoint-1600/optimizer.pt b/checkpoint-1600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6930d510ab71a672f095b199a270d3056f4a7b60
--- /dev/null
+++ b/checkpoint-1600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a3d7f9f91db412b6ce432714182422202e4a858c868a464e530597d63bc934
+size 7433594
diff --git a/checkpoint-1600/rng_state.pth b/checkpoint-1600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..df2a013b58dccbd0d383abcb10944297e155f58c
--- /dev/null
+++ b/checkpoint-1600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da10fd0dc4281cc8906f40adc00a6ebd1867abdeadf3602640e25ca4449c6630
+size 14244
diff --git a/checkpoint-1600/scheduler.pt b/checkpoint-1600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f4a71877e40d824ed6f34c9e1dc6df004a4da727
--- /dev/null
+++ b/checkpoint-1600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f808986c8e680a605b465bc14eeb4fba94c0c8f4e9ad8bd8334ede3febe21b4
+size 1064
diff --git a/checkpoint-1600/special_tokens_map.json b/checkpoint-1600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1600/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1600/tokenizer.model b/checkpoint-1600/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1600/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1600/tokenizer_config.json b/checkpoint-1600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1600/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1600/trainer_state.json b/checkpoint-1600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6582f7e50f660bfb79fbd8fcae5203cea9853113
--- /dev/null
+++ b/checkpoint-1600/trainer_state.json
@@ -0,0 +1,1269 @@
+{
+  "best_metric": 1.4853577613830566,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1600",
+  "epoch": 2.8444444444444446,
+  "eval_steps": 100,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.2453933766709084e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1600/training_args.bin b/checkpoint-1600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1700/README.md b/checkpoint-1700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1700/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1700/adapter_config.json b/checkpoint-1700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1700/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1700/adapter_model.safetensors b/checkpoint-1700/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77df282344e3816f312621cd121f4dd2ede731eb
--- /dev/null
+++ b/checkpoint-1700/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6dbff24086204d0d9d21e15cf4610f602c5dc5f8c0c7c27c825b9dd3b944d1
+size 3695848
diff --git a/checkpoint-1700/optimizer.pt b/checkpoint-1700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ce4d0fc5b5c572e596b983cd4664418ab581c3ea
--- /dev/null
+++ b/checkpoint-1700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09320c0a6d3dc01e2a102435328998e5b8c897d519fe03076893261d774f9c92
+size 7433594
diff --git a/checkpoint-1700/rng_state.pth b/checkpoint-1700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e19ae8362b9d3c7a143e8c04778152446d252b1b
--- /dev/null
+++ b/checkpoint-1700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852f3fd5f1617fef0127cb60fc7f76662bb7f88dccf08de78bbe18396f9a5465
+size 14244
diff --git a/checkpoint-1700/scheduler.pt b/checkpoint-1700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..14d49e8d5035bde5b5860b1241687a60cf510f59
--- /dev/null
+++ b/checkpoint-1700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f34ed12275ce8cb3775cded317a2ea6bc16fa2d373c2282f4903eede5b8afe4
+size 1064
diff --git a/checkpoint-1700/special_tokens_map.json b/checkpoint-1700/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1700/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1700/tokenizer.model b/checkpoint-1700/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1700/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1700/tokenizer_config.json b/checkpoint-1700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1700/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1700/trainer_state.json b/checkpoint-1700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..488586eabb14abc0c3d8e11773d05cb8e7e2ae10
--- /dev/null
+++ b/checkpoint-1700/trainer_state.json
@@ -0,0 +1,1347 @@
+{
+  "best_metric": 1.478974461555481,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1700",
+  "epoch": 3.022222222222222,
+  "eval_steps": 100,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.3237080942080164e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1700/training_args.bin b/checkpoint-1700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1800/README.md b/checkpoint-1800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1800/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1800/adapter_config.json b/checkpoint-1800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1800/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1800/adapter_model.safetensors b/checkpoint-1800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..37765c01612761bfa18b5cc486d50f5a80bfdf97
--- /dev/null
+++ b/checkpoint-1800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd843fe29d28ffe48a4058c2eb56cf10f2e4def7ace9ed8ba244389ab6da424d
+size 3695848
diff --git a/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..589a12b10bec59692fd40fec64d429acb0141bd9
--- /dev/null
+++ b/checkpoint-1800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b339d3da14343ee9b9148bdf6adcf4efaa5b6e5bb21aa29f51877eb2cf9216
+size 7433594
diff --git a/checkpoint-1800/rng_state.pth b/checkpoint-1800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..64f10103443a944533eac35c97bdab8689d0cf78
--- /dev/null
+++ b/checkpoint-1800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa9e4828b11bf3e5db5b676ee88c74008c62baa76f1779d97fad40fad2af7dc
+size 14244
diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..23a3a937f7ff479251b776f1c96682906e2f8ec1
--- /dev/null
+++ b/checkpoint-1800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ee1bbef9189a4d6d68b66bb79821f46d27258850903ab7df408b4a372d7f34
+size 1064
diff --git a/checkpoint-1800/special_tokens_map.json b/checkpoint-1800/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1800/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1800/tokenizer.model b/checkpoint-1800/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1800/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1800/tokenizer_config.json b/checkpoint-1800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1800/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9971f0a80c41633637137ddb0751e73335b56883
--- /dev/null
+++ b/checkpoint-1800/trainer_state.json
@@ -0,0 +1,1425 @@
+{
+  "best_metric": 1.4779504537582397,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1800",
+  "epoch": 3.2,
+  "eval_steps": 100,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 4.43009090423584,
+      "learning_rate": 3.94219716271167e-05,
+      "loss": 1.3304,
+      "step": 1710
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 4.001712799072266,
+      "learning_rate": 3.930759447905298e-05,
+      "loss": 1.3534,
+      "step": 1720
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 4.664085388183594,
+      "learning_rate": 3.919277024340891e-05,
+      "loss": 1.368,
+      "step": 1730
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 4.42681360244751,
+      "learning_rate": 3.907750250824327e-05,
+      "loss": 1.4164,
+      "step": 1740
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 7.331808567047119,
+      "learning_rate": 3.8961794875473394e-05,
+      "loss": 1.4333,
+      "step": 1750
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 5.612239837646484,
+      "learning_rate": 3.884565096076269e-05,
+      "loss": 1.5754,
+      "step": 1760
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 5.236481666564941,
+      "learning_rate": 3.872907439340758e-05,
+      "loss": 1.4017,
+      "step": 1770
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 4.995403289794922,
+      "learning_rate": 3.861206881622419e-05,
+      "loss": 1.5011,
+      "step": 1780
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 41.0167236328125,
+      "learning_rate": 3.8494637885434396e-05,
+      "loss": 1.4472,
+      "step": 1790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.136650562286377,
+      "learning_rate": 3.837678527055168e-05,
+      "loss": 1.3939,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.4779504537582397,
+      "eval_runtime": 124.6728,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.4031463107723264e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-1900/README.md b/checkpoint-1900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-1900/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-1900/adapter_config.json b/checkpoint-1900/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-1900/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-1900/adapter_model.safetensors b/checkpoint-1900/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..aaf94f6146a9ac40025436b6af78f2aaf8d23d63
--- /dev/null
+++ b/checkpoint-1900/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5c8176c4bf9cc1494f5db12726e6962dc5bd6899855d36e1a88e187fa0f41e
+size 3695848
diff --git a/checkpoint-1900/optimizer.pt b/checkpoint-1900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0fc890fff8e5481259044266e236ba8aad8b57c3
--- /dev/null
+++ b/checkpoint-1900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55409586050dc946264e51e79838642d3e1367cee298211e7922245f5dd8c331
+size 7433594
diff --git a/checkpoint-1900/rng_state.pth b/checkpoint-1900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8fec1b8ead84658fd34d030dbea89657122e87e4
--- /dev/null
+++ b/checkpoint-1900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ec95f4c38d7d08b93c7ccf1ae68fe2d234a875add515be76cb3882595dff2c
+size 14244
diff --git a/checkpoint-1900/scheduler.pt b/checkpoint-1900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..78d01dad912b67e9dada64bbca5f3da5066b4022
--- /dev/null
+++ b/checkpoint-1900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97f86040ef74c987109342a3078b56769fa70b7735a911f2cdf1c4f4e7da4c0
+size 1064
diff --git a/checkpoint-1900/special_tokens_map.json b/checkpoint-1900/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-1900/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1900/tokenizer.model b/checkpoint-1900/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-1900/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-1900/tokenizer_config.json b/checkpoint-1900/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-1900/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1900/trainer_state.json b/checkpoint-1900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..befd3ff8d0106b1efc372047c151703931646b52
--- /dev/null
+++ b/checkpoint-1900/trainer_state.json
@@ -0,0 +1,1503 @@
+{
+  "best_metric": 1.4685039520263672,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-1900",
+  "epoch": 3.3777777777777778,
+  "eval_steps": 100,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 4.43009090423584,
+      "learning_rate": 3.94219716271167e-05,
+      "loss": 1.3304,
+      "step": 1710
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 4.001712799072266,
+      "learning_rate": 3.930759447905298e-05,
+      "loss": 1.3534,
+      "step": 1720
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 4.664085388183594,
+      "learning_rate": 3.919277024340891e-05,
+      "loss": 1.368,
+      "step": 1730
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 4.42681360244751,
+      "learning_rate": 3.907750250824327e-05,
+      "loss": 1.4164,
+      "step": 1740
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 7.331808567047119,
+      "learning_rate": 3.8961794875473394e-05,
+      "loss": 1.4333,
+      "step": 1750
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 5.612239837646484,
+      "learning_rate": 3.884565096076269e-05,
+      "loss": 1.5754,
+      "step": 1760
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 5.236481666564941,
+      "learning_rate": 3.872907439340758e-05,
+      "loss": 1.4017,
+      "step": 1770
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 4.995403289794922,
+      "learning_rate": 3.861206881622419e-05,
+      "loss": 1.5011,
+      "step": 1780
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 41.0167236328125,
+      "learning_rate": 3.8494637885434396e-05,
+      "loss": 1.4472,
+      "step": 1790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.136650562286377,
+      "learning_rate": 3.837678527055168e-05,
+      "loss": 1.3939,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.4779504537582397,
+      "eval_runtime": 124.6728,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 1800
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.178096294403076,
+      "learning_rate": 3.8258514654266434e-05,
+      "loss": 1.5265,
+      "step": 1810
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 6.949739456176758,
+      "learning_rate": 3.813982973233083e-05,
+      "loss": 1.3674,
+      "step": 1820
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 3.84801983833313,
+      "learning_rate": 3.802073421344339e-05,
+      "loss": 1.4305,
+      "step": 1830
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 3.5803613662719727,
+      "learning_rate": 3.7901231819133105e-05,
+      "loss": 1.557,
+      "step": 1840
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 3.509099245071411,
+      "learning_rate": 3.7781326283643085e-05,
+      "loss": 1.3611,
+      "step": 1850
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 41.185279846191406,
+      "learning_rate": 3.766102135381393e-05,
+      "loss": 1.3944,
+      "step": 1860
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.797672748565674,
+      "learning_rate": 3.75403207889666e-05,
+      "loss": 1.2557,
+      "step": 1870
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 4.237602233886719,
+      "learning_rate": 3.741922836078499e-05,
+      "loss": 1.3583,
+      "step": 1880
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.5037312507629395,
+      "learning_rate": 3.729774785319801e-05,
+      "loss": 1.4619,
+      "step": 1890
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 4.292742729187012,
+      "learning_rate": 3.717588306226143e-05,
+      "loss": 1.3986,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 1.4685039520263672,
+      "eval_runtime": 124.7126,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.005,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.4782532316010906e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1900/training_args.bin b/checkpoint-1900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-1900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-200/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-200/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b0ededaa496b9da879d66b42fb81654306f2ef70
--- /dev/null
+++ b/checkpoint-200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f47a66591776a9b27423c2d590268a4c1459646318aa8fd05788e737092ff4e
+size 3695848
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ea9609212aabd8f64e9eac7492d220ccdb65879
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c402a3caca01a40b86e20628c7085372b9f06b9ad905962d0ae3e46afa5b7d
+size 7433594
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f117a9ad349640db82853b066f18de7c76959ba5
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25dae3a1acf89a39570fafa2dbe3168373e743792e659c1c98646a426968d3c
+size 14244
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8c24fcb68a3ab42506f78b055ff7780d68049a44
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0138d0ffd6b4d8f6ded7f39531698ac8be82688a7f3f9e5696c883e0b215f9f2
+size 1064
diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-200/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-200/tokenizer.model b/checkpoint-200/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-200/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-200/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..17a92d70c32a4b91e35394c87947a4938402b90c
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,177 @@
+{
+  "best_metric": 1.8619400262832642,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-200",
+  "epoch": 0.35555555555555557,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.5694713402792346e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-2000/README.md b/checkpoint-2000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-2000/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-2000/adapter_config.json b/checkpoint-2000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-2000/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-2000/adapter_model.safetensors b/checkpoint-2000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7ee1f8cd2c711f999d6787d9dea5288c280a3a3
--- /dev/null
+++ b/checkpoint-2000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49cbee4dd4e55f624520dd6d6ce72e1ebb246fb2cad3777a8fdb8c4dfd08838a
+size 3695848
diff --git a/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cdefc4c22f67fe24f9e9d0b494eacf4bca48baab
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea2c1be3bc67de972e9e0ad95457b8459b5296753a9c15b9659fc6c6e2acacf
+size 7433594
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a7c8891a134cb419fd6419b4ddb3f353c4aaa4af
--- /dev/null
+++ b/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cfbca8f6aded8567dbf52663fad88626e9ff81399d30f9b4324b100df00d2e8
+size 14244
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..687cb76d309cbe40e66529e32e946c78f8bdb487
--- /dev/null
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfba70f1616c3f7d458e303ed4473e7aa0762778705b8ca6aad7e7472d25014b
+size 1064
diff --git a/checkpoint-2000/special_tokens_map.json b/checkpoint-2000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-2000/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-2000/tokenizer.model b/checkpoint-2000/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-2000/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-2000/tokenizer_config.json b/checkpoint-2000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1ca5d0e4bfb57828c3eab9fb172d0877267c8117
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,1581 @@
+{
+  "best_metric": 1.4598569869995117,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-2000",
+  "epoch": 3.5555555555555554,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 4.43009090423584,
+      "learning_rate": 3.94219716271167e-05,
+      "loss": 1.3304,
+      "step": 1710
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 4.001712799072266,
+      "learning_rate": 3.930759447905298e-05,
+      "loss": 1.3534,
+      "step": 1720
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 4.664085388183594,
+      "learning_rate": 3.919277024340891e-05,
+      "loss": 1.368,
+      "step": 1730
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 4.42681360244751,
+      "learning_rate": 3.907750250824327e-05,
+      "loss": 1.4164,
+      "step": 1740
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 7.331808567047119,
+      "learning_rate": 3.8961794875473394e-05,
+      "loss": 1.4333,
+      "step": 1750
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 5.612239837646484,
+      "learning_rate": 3.884565096076269e-05,
+      "loss": 1.5754,
+      "step": 1760
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 5.236481666564941,
+      "learning_rate": 3.872907439340758e-05,
+      "loss": 1.4017,
+      "step": 1770
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 4.995403289794922,
+      "learning_rate": 3.861206881622419e-05,
+      "loss": 1.5011,
+      "step": 1780
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 41.0167236328125,
+      "learning_rate": 3.8494637885434396e-05,
+      "loss": 1.4472,
+      "step": 1790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.136650562286377,
+      "learning_rate": 3.837678527055168e-05,
+      "loss": 1.3939,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.4779504537582397,
+      "eval_runtime": 124.6728,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 1800
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.178096294403076,
+      "learning_rate": 3.8258514654266434e-05,
+      "loss": 1.5265,
+      "step": 1810
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 6.949739456176758,
+      "learning_rate": 3.813982973233083e-05,
+      "loss": 1.3674,
+      "step": 1820
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 3.84801983833313,
+      "learning_rate": 3.802073421344339e-05,
+      "loss": 1.4305,
+      "step": 1830
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 3.5803613662719727,
+      "learning_rate": 3.7901231819133105e-05,
+      "loss": 1.557,
+      "step": 1840
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 3.509099245071411,
+      "learning_rate": 3.7781326283643085e-05,
+      "loss": 1.3611,
+      "step": 1850
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 41.185279846191406,
+      "learning_rate": 3.766102135381393e-05,
+      "loss": 1.3944,
+      "step": 1860
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.797672748565674,
+      "learning_rate": 3.75403207889666e-05,
+      "loss": 1.2557,
+      "step": 1870
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 4.237602233886719,
+      "learning_rate": 3.741922836078499e-05,
+      "loss": 1.3583,
+      "step": 1880
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.5037312507629395,
+      "learning_rate": 3.729774785319801e-05,
+      "loss": 1.4619,
+      "step": 1890
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 4.292742729187012,
+      "learning_rate": 3.717588306226143e-05,
+      "loss": 1.3986,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 1.4685039520263672,
+      "eval_runtime": 124.7126,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.005,
+      "step": 1900
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.198277950286865,
+      "learning_rate": 3.705363779603917e-05,
+      "loss": 1.349,
+      "step": 1910
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 3.86722469329834,
+      "learning_rate": 3.693101587448436e-05,
+      "loss": 1.5053,
+      "step": 1920
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 8.68099594116211,
+      "learning_rate": 3.680802112931996e-05,
+      "loss": 1.3899,
+      "step": 1930
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 3.8347198963165283,
+      "learning_rate": 3.6684657403919005e-05,
+      "loss": 1.4519,
+      "step": 1940
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 9.875212669372559,
+      "learning_rate": 3.6560928553184554e-05,
+      "loss": 1.4788,
+      "step": 1950
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 8.638535499572754,
+      "learning_rate": 3.6436838443429175e-05,
+      "loss": 1.3777,
+      "step": 1960
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 3.73545503616333,
+      "learning_rate": 3.631239095225417e-05,
+      "loss": 1.4962,
+      "step": 1970
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 8.485962867736816,
+      "learning_rate": 3.618758996842839e-05,
+      "loss": 1.4377,
+      "step": 1980
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 4.3264055252075195,
+      "learning_rate": 3.60624393917667e-05,
+      "loss": 1.5695,
+      "step": 1990
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 3.979128837585449,
+      "learning_rate": 3.5936943133008183e-05,
+      "loss": 1.2959,
+      "step": 2000
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 1.4598569869995117,
+      "eval_runtime": 124.8036,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.558141521683153e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-2100/README.md b/checkpoint-2100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-2100/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-2100/adapter_config.json b/checkpoint-2100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-2100/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-2100/adapter_model.safetensors b/checkpoint-2100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..28d39b2250045331a552389758d776972565a55a
--- /dev/null
+++ b/checkpoint-2100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b004da8334249609efdffe2262b682ded1a8d2becb9c74047796455c2409ff6
+size 3695848
diff --git a/checkpoint-2100/optimizer.pt b/checkpoint-2100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f684714ec16dee5ed3d89c71791ebb385784330d
--- /dev/null
+++ b/checkpoint-2100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4df76ca3b66c695125bee6844320ea7ff57edeab757c5c7f29352c9c04494e
+size 7433594
diff --git a/checkpoint-2100/rng_state.pth b/checkpoint-2100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..281716a99e271d14df76be4655ee8ca5c529b42b
--- /dev/null
+++ b/checkpoint-2100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f086cae8ff126f7717bbbbd3e116e9f2b7d1d450451adf89edaa599c3499bd
+size 14244
diff --git a/checkpoint-2100/scheduler.pt b/checkpoint-2100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c09c3d669471aedd2a184337b878e09b413021a3
--- /dev/null
+++ b/checkpoint-2100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4302be746dbdc6f036e55f2f42bca31244286c53ab241fbecfbcb971d62c9a2c
+size 1064
diff --git a/checkpoint-2100/special_tokens_map.json b/checkpoint-2100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-2100/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-2100/tokenizer.model b/checkpoint-2100/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-2100/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-2100/tokenizer_config.json b/checkpoint-2100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-2100/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-2100/trainer_state.json b/checkpoint-2100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d02884e6e215971e9b2ab41a898df8230e3ea831
--- /dev/null
+++ b/checkpoint-2100/trainer_state.json
@@ -0,0 +1,1659 @@
+{
+  "best_metric": 1.4545879364013672,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-2100",
+  "epoch": 3.7333333333333334,
+  "eval_steps": 100,
+  "global_step": 2100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 4.43009090423584,
+      "learning_rate": 3.94219716271167e-05,
+      "loss": 1.3304,
+      "step": 1710
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 4.001712799072266,
+      "learning_rate": 3.930759447905298e-05,
+      "loss": 1.3534,
+      "step": 1720
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 4.664085388183594,
+      "learning_rate": 3.919277024340891e-05,
+      "loss": 1.368,
+      "step": 1730
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 4.42681360244751,
+      "learning_rate": 3.907750250824327e-05,
+      "loss": 1.4164,
+      "step": 1740
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 7.331808567047119,
+      "learning_rate": 3.8961794875473394e-05,
+      "loss": 1.4333,
+      "step": 1750
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 5.612239837646484,
+      "learning_rate": 3.884565096076269e-05,
+      "loss": 1.5754,
+      "step": 1760
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 5.236481666564941,
+      "learning_rate": 3.872907439340758e-05,
+      "loss": 1.4017,
+      "step": 1770
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 4.995403289794922,
+      "learning_rate": 3.861206881622419e-05,
+      "loss": 1.5011,
+      "step": 1780
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 41.0167236328125,
+      "learning_rate": 3.8494637885434396e-05,
+      "loss": 1.4472,
+      "step": 1790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.136650562286377,
+      "learning_rate": 3.837678527055168e-05,
+      "loss": 1.3939,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.4779504537582397,
+      "eval_runtime": 124.6728,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 1800
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.178096294403076,
+      "learning_rate": 3.8258514654266434e-05,
+      "loss": 1.5265,
+      "step": 1810
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 6.949739456176758,
+      "learning_rate": 3.813982973233083e-05,
+      "loss": 1.3674,
+      "step": 1820
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 3.84801983833313,
+      "learning_rate": 3.802073421344339e-05,
+      "loss": 1.4305,
+      "step": 1830
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 3.5803613662719727,
+      "learning_rate": 3.7901231819133105e-05,
+      "loss": 1.557,
+      "step": 1840
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 3.509099245071411,
+      "learning_rate": 3.7781326283643085e-05,
+      "loss": 1.3611,
+      "step": 1850
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 41.185279846191406,
+      "learning_rate": 3.766102135381393e-05,
+      "loss": 1.3944,
+      "step": 1860
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.797672748565674,
+      "learning_rate": 3.75403207889666e-05,
+      "loss": 1.2557,
+      "step": 1870
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 4.237602233886719,
+      "learning_rate": 3.741922836078499e-05,
+      "loss": 1.3583,
+      "step": 1880
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.5037312507629395,
+      "learning_rate": 3.729774785319801e-05,
+      "loss": 1.4619,
+      "step": 1890
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 4.292742729187012,
+      "learning_rate": 3.717588306226143e-05,
+      "loss": 1.3986,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 1.4685039520263672,
+      "eval_runtime": 124.7126,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.005,
+      "step": 1900
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.198277950286865,
+      "learning_rate": 3.705363779603917e-05,
+      "loss": 1.349,
+      "step": 1910
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 3.86722469329834,
+      "learning_rate": 3.693101587448436e-05,
+      "loss": 1.5053,
+      "step": 1920
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 8.68099594116211,
+      "learning_rate": 3.680802112931996e-05,
+      "loss": 1.3899,
+      "step": 1930
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 3.8347198963165283,
+      "learning_rate": 3.6684657403919005e-05,
+      "loss": 1.4519,
+      "step": 1940
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 9.875212669372559,
+      "learning_rate": 3.6560928553184554e-05,
+      "loss": 1.4788,
+      "step": 1950
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 8.638535499572754,
+      "learning_rate": 3.6436838443429175e-05,
+      "loss": 1.3777,
+      "step": 1960
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 3.73545503616333,
+      "learning_rate": 3.631239095225417e-05,
+      "loss": 1.4962,
+      "step": 1970
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 8.485962867736816,
+      "learning_rate": 3.618758996842839e-05,
+      "loss": 1.4377,
+      "step": 1980
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 4.3264055252075195,
+      "learning_rate": 3.60624393917667e-05,
+      "loss": 1.5695,
+      "step": 1990
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 3.979128837585449,
+      "learning_rate": 3.5936943133008183e-05,
+      "loss": 1.2959,
+      "step": 2000
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 1.4598569869995117,
+      "eval_runtime": 124.8036,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 2000
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 7.0864338874816895,
+      "learning_rate": 3.581110511369384e-05,
+      "loss": 1.4301,
+      "step": 2010
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 4.597893714904785,
+      "learning_rate": 3.568492926604412e-05,
+      "loss": 1.2962,
+      "step": 2020
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 3.7413573265075684,
+      "learning_rate": 3.555841953283603e-05,
+      "loss": 1.3708,
+      "step": 2030
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 4.206364631652832,
+      "learning_rate": 3.5431579867279905e-05,
+      "loss": 1.4758,
+      "step": 2040
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 5.203850269317627,
+      "learning_rate": 3.530441423289591e-05,
+      "loss": 1.4563,
+      "step": 2050
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 3.0671565532684326,
+      "learning_rate": 3.517692660339018e-05,
+      "loss": 1.322,
+      "step": 2060
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 4.655951499938965,
+      "learning_rate": 3.504912096253061e-05,
+      "loss": 1.4868,
+      "step": 2070
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 3.5286195278167725,
+      "learning_rate": 3.492100130402242e-05,
+      "loss": 1.3379,
+      "step": 2080
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 3.526078701019287,
+      "learning_rate": 3.479257163138334e-05,
+      "loss": 1.4864,
+      "step": 2090
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 4.072696208953857,
+      "learning_rate": 3.4663835957818515e-05,
+      "loss": 1.4187,
+      "step": 2100
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 1.4545879364013672,
+      "eval_runtime": 124.6694,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.6370752708179395e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2100/training_args.bin b/checkpoint-2100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-2100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-2200/README.md b/checkpoint-2200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-2200/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-2200/adapter_config.json b/checkpoint-2200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-2200/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-2200/adapter_model.safetensors b/checkpoint-2200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8651fe97ee81a004df96ae95db9ce4d24986ab7a
--- /dev/null
+++ b/checkpoint-2200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c0821969cba83fb4ddfe3e06c4f9b790b26ed38f568a4fdcb10d728880fa89
+size 3695848
diff --git a/checkpoint-2200/optimizer.pt b/checkpoint-2200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43804723f02033ac47be532983b43b3b590c35c9
--- /dev/null
+++ b/checkpoint-2200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11261f4953e1e480fe038bc9455756601f7957d51e38997af816f1e735e46cb4
+size 7433594
diff --git a/checkpoint-2200/rng_state.pth b/checkpoint-2200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8dfec0828a7402797682cd12944ac94c10f781d0
--- /dev/null
+++ b/checkpoint-2200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1b45396351f9be4812299398594de84d4ac97cdb52933bc1794e751252fcab
+size 14244
diff --git a/checkpoint-2200/scheduler.pt b/checkpoint-2200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84b3806e5c6261722acd7af77ac5a1b89c846c9f
--- /dev/null
+++ b/checkpoint-2200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a23d8473e9043fe4710673fa5c72b13b7436a0f6a39c0d85ebd8b538a79f02
+size 1064
diff --git a/checkpoint-2200/special_tokens_map.json b/checkpoint-2200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-2200/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-2200/tokenizer.model b/checkpoint-2200/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-2200/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-2200/tokenizer_config.json b/checkpoint-2200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-2200/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-2200/trainer_state.json b/checkpoint-2200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..025d8f96a4bb52378ab725344d2fee8874935148
--- /dev/null
+++ b/checkpoint-2200/trainer_state.json
@@ -0,0 +1,1737 @@
+{
+  "best_metric": 1.4545879364013672,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-2100",
+  "epoch": 3.911111111111111,
+  "eval_steps": 100,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.806954383850098,
+      "learning_rate": 4.683455682293863e-05,
+      "loss": 1.6824,
+      "step": 910
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 5.980200290679932,
+      "learning_rate": 4.676615257088776e-05,
+      "loss": 1.5989,
+      "step": 920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 4.3645429611206055,
+      "learning_rate": 4.6697068164216896e-05,
+      "loss": 1.6469,
+      "step": 930
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2400012016296387,
+      "learning_rate": 4.662730576169423e-05,
+      "loss": 1.568,
+      "step": 940
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 4.331827640533447,
+      "learning_rate": 4.6556867543274184e-05,
+      "loss": 1.5236,
+      "step": 950
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.3798201084136963,
+      "learning_rate": 4.6485755710029256e-05,
+      "loss": 1.5046,
+      "step": 960
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 5.440864086151123,
+      "learning_rate": 4.6413972484081216e-05,
+      "loss": 1.5816,
+      "step": 970
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.852995872497559,
+      "learning_rate": 4.6341520108531746e-05,
+      "loss": 1.4193,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.2782206535339355,
+      "learning_rate": 4.626840084739224e-05,
+      "loss": 1.5457,
+      "step": 990
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 8.631403923034668,
+      "learning_rate": 4.619461698551315e-05,
+      "loss": 1.652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 1.5386379957199097,
+      "eval_runtime": 124.8384,
+      "eval_samples_per_second": 8.01,
+      "eval_steps_per_second": 2.003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.581122875213623,
+      "learning_rate": 4.612017082851253e-05,
+      "loss": 1.5746,
+      "step": 1010
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.0373165607452393,
+      "learning_rate": 4.604506470270403e-05,
+      "loss": 1.6038,
+      "step": 1020
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.5066914558410645,
+      "learning_rate": 4.5969300955024167e-05,
+      "loss": 1.5725,
+      "step": 1030
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.402235507965088,
+      "learning_rate": 4.589288195295901e-05,
+      "loss": 1.5469,
+      "step": 1040
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 4.844370365142822,
+      "learning_rate": 4.58158100844702e-05,
+      "loss": 1.5424,
+      "step": 1050
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.146657943725586,
+      "learning_rate": 4.573808775792033e-05,
+      "loss": 1.4878,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.210528612136841,
+      "learning_rate": 4.5659717401997655e-05,
+      "loss": 1.6077,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.2232818603515625,
+      "learning_rate": 4.5580701465640254e-05,
+      "loss": 1.4824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.8741068840026855,
+      "learning_rate": 4.550104241795946e-05,
+      "loss": 1.6172,
+      "step": 1090
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 8.092519760131836,
+      "learning_rate": 4.5420742748162734e-05,
+      "loss": 1.3659,
+      "step": 1100
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 1.5198711156845093,
+      "eval_runtime": 124.8546,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1100
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.068336009979248,
+      "learning_rate": 4.5339804965475875e-05,
+      "loss": 1.4661,
+      "step": 1110
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 13.167552947998047,
+      "learning_rate": 4.525823159906459e-05,
+      "loss": 1.411,
+      "step": 1120
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 4.712369918823242,
+      "learning_rate": 4.5176025197955494e-05,
+      "loss": 1.3309,
+      "step": 1130
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 7.261610507965088,
+      "learning_rate": 4.509318833095642e-05,
+      "loss": 1.3892,
+      "step": 1140
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.8006956577301025,
+      "learning_rate": 4.500972358657618e-05,
+      "loss": 1.3927,
+      "step": 1150
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 3.6301958560943604,
+      "learning_rate": 4.492563357294369e-05,
+      "loss": 1.4629,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.353027820587158,
+      "learning_rate": 4.4840920917726426e-05,
+      "loss": 1.352,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.375173807144165,
+      "learning_rate": 4.475558826804833e-05,
+      "loss": 1.4096,
+      "step": 1180
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 6.289668560028076,
+      "learning_rate": 4.466963829040712e-05,
+      "loss": 1.4834,
+      "step": 1190
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 4.517002582550049,
+      "learning_rate": 4.458307367059092e-05,
+      "loss": 1.4746,
+      "step": 1200
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.5145190954208374,
+      "eval_runtime": 124.8898,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 1200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.195769786834717,
+      "learning_rate": 4.449589711359438e-05,
+      "loss": 1.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.751405715942383,
+      "learning_rate": 4.440811134353412e-05,
+      "loss": 1.5501,
+      "step": 1220
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 4.148709774017334,
+      "learning_rate": 4.431971910356363e-05,
+      "loss": 1.5253,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 20.003253936767578,
+      "learning_rate": 4.42307231557875e-05,
+      "loss": 1.6413,
+      "step": 1240
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.721023082733154,
+      "learning_rate": 4.414112628117517e-05,
+      "loss": 1.5608,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.672358989715576,
+      "learning_rate": 4.4050931279474015e-05,
+      "loss": 1.3646,
+      "step": 1260
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 4.073034286499023,
+      "learning_rate": 4.396014096912182e-05,
+      "loss": 1.3499,
+      "step": 1270
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 3.2312991619110107,
+      "learning_rate": 4.386875818715874e-05,
+      "loss": 1.4648,
+      "step": 1280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 18.92267417907715,
+      "learning_rate": 4.3776785789138675e-05,
+      "loss": 1.4919,
+      "step": 1290
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 5.677367687225342,
+      "learning_rate": 4.368422664903997e-05,
+      "loss": 1.2891,
+      "step": 1300
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 1.504623532295227,
+      "eval_runtime": 124.8541,
+      "eval_samples_per_second": 8.009,
+      "eval_steps_per_second": 2.002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 5.031940460205078,
+      "learning_rate": 4.359108365917565e-05,
+      "loss": 1.4939,
+      "step": 1310
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 7.701929092407227,
+      "learning_rate": 4.349735973010305e-05,
+      "loss": 1.28,
+      "step": 1320
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 5.7498040199279785,
+      "learning_rate": 4.3403057790532855e-05,
+      "loss": 1.4584,
+      "step": 1330
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 8.7277193069458,
+      "learning_rate": 4.330818078723755e-05,
+      "loss": 1.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.915125846862793,
+      "learning_rate": 4.32127316849594e-05,
+      "loss": 1.3794,
+      "step": 1350
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.949733018875122,
+      "learning_rate": 4.311671346631774e-05,
+      "loss": 1.3543,
+      "step": 1360
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 5.377658843994141,
+      "learning_rate": 4.302012913171584e-05,
+      "loss": 1.3695,
+      "step": 1370
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 16.94107437133789,
+      "learning_rate": 4.292298169924709e-05,
+      "loss": 1.5168,
+      "step": 1380
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.190367221832275,
+      "learning_rate": 4.282527420460072e-05,
+      "loss": 1.4058,
+      "step": 1390
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 9.269573211669922,
+      "learning_rate": 4.272700970096696e-05,
+      "loss": 1.5794,
+      "step": 1400
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.498180627822876,
+      "eval_runtime": 124.7222,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.004,
+      "step": 1400
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 3.951293468475342,
+      "learning_rate": 4.262819125894156e-05,
+      "loss": 1.56,
+      "step": 1410
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8725697994232178,
+      "learning_rate": 4.252882196642992e-05,
+      "loss": 1.5159,
+      "step": 1420
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.898501396179199,
+      "learning_rate": 4.242890492855056e-05,
+      "loss": 1.4659,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.807662487030029,
+      "learning_rate": 4.23284432675381e-05,
+      "loss": 1.5736,
+      "step": 1440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.529371500015259,
+      "learning_rate": 4.222744012264566e-05,
+      "loss": 1.5011,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.336548805236816,
+      "learning_rate": 4.212589865004684e-05,
+      "loss": 1.6629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 6.222330093383789,
+      "learning_rate": 4.2023822022737016e-05,
+      "loss": 1.5573,
+      "step": 1470
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 4.25172233581543,
+      "learning_rate": 4.192121343043424e-05,
+      "loss": 1.3817,
+      "step": 1480
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 4.487111568450928,
+      "learning_rate": 4.181807607947954e-05,
+      "loss": 1.5323,
+      "step": 1490
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 4.656155109405518,
+      "learning_rate": 4.1714413192736754e-05,
+      "loss": 1.3678,
+      "step": 1500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.5049968957901,
+      "eval_runtime": 124.7803,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.004,
+      "step": 1500
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 4.431355953216553,
+      "learning_rate": 4.161022800949177e-05,
+      "loss": 1.486,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 18.211524963378906,
+      "learning_rate": 4.150552378535137e-05,
+      "loss": 1.4498,
+      "step": 1520
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 5.3755292892456055,
+      "learning_rate": 4.140030379214147e-05,
+      "loss": 1.4421,
+      "step": 1530
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.626212120056152,
+      "learning_rate": 4.1294571317804854e-05,
+      "loss": 1.4322,
+      "step": 1540
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 4.030793190002441,
+      "learning_rate": 4.1188329666298464e-05,
+      "loss": 1.3433,
+      "step": 1550
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 6.53309440612793,
+      "learning_rate": 4.108158215749014e-05,
+      "loss": 1.5604,
+      "step": 1560
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.76047420501709,
+      "learning_rate": 4.0974332127054914e-05,
+      "loss": 1.3259,
+      "step": 1570
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 4.58742094039917,
+      "learning_rate": 4.0866582926370725e-05,
+      "loss": 1.4228,
+      "step": 1580
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 4.566816806793213,
+      "learning_rate": 4.0758337922413716e-05,
+      "loss": 1.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.218478202819824,
+      "learning_rate": 4.064960049765304e-05,
+      "loss": 1.5061,
+      "step": 1600
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.4853577613830566,
+      "eval_runtime": 124.7889,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 2.003,
+      "step": 1600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 13.811309814453125,
+      "learning_rate": 4.054037404994516e-05,
+      "loss": 1.4839,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.560975074768066,
+      "learning_rate": 4.043066199242762e-05,
+      "loss": 1.4765,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 35.27302551269531,
+      "learning_rate": 4.032046775341247e-05,
+      "loss": 1.4105,
+      "step": 1630
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 4.9896745681762695,
+      "learning_rate": 4.020979477627907e-05,
+      "loss": 1.5688,
+      "step": 1640
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.5250892639160156,
+      "learning_rate": 4.0098646519366534e-05,
+      "loss": 1.4484,
+      "step": 1650
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 5.281729698181152,
+      "learning_rate": 3.998702645586565e-05,
+      "loss": 1.6017,
+      "step": 1660
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 4.667525768280029,
+      "learning_rate": 3.9874938073710336e-05,
+      "loss": 1.5006,
+      "step": 1670
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 4.294438362121582,
+      "learning_rate": 3.976238487546864e-05,
+      "loss": 1.4218,
+      "step": 1680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.070734977722168,
+      "learning_rate": 3.9649370378233365e-05,
+      "loss": 1.6569,
+      "step": 1690
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 4.640359878540039,
+      "learning_rate": 3.953589811351204e-05,
+      "loss": 1.5635,
+      "step": 1700
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 1.478974461555481,
+      "eval_runtime": 124.6852,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 1700
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 4.43009090423584,
+      "learning_rate": 3.94219716271167e-05,
+      "loss": 1.3304,
+      "step": 1710
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 4.001712799072266,
+      "learning_rate": 3.930759447905298e-05,
+      "loss": 1.3534,
+      "step": 1720
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 4.664085388183594,
+      "learning_rate": 3.919277024340891e-05,
+      "loss": 1.368,
+      "step": 1730
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 4.42681360244751,
+      "learning_rate": 3.907750250824327e-05,
+      "loss": 1.4164,
+      "step": 1740
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 7.331808567047119,
+      "learning_rate": 3.8961794875473394e-05,
+      "loss": 1.4333,
+      "step": 1750
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 5.612239837646484,
+      "learning_rate": 3.884565096076269e-05,
+      "loss": 1.5754,
+      "step": 1760
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 5.236481666564941,
+      "learning_rate": 3.872907439340758e-05,
+      "loss": 1.4017,
+      "step": 1770
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 4.995403289794922,
+      "learning_rate": 3.861206881622419e-05,
+      "loss": 1.5011,
+      "step": 1780
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 41.0167236328125,
+      "learning_rate": 3.8494637885434396e-05,
+      "loss": 1.4472,
+      "step": 1790
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.136650562286377,
+      "learning_rate": 3.837678527055168e-05,
+      "loss": 1.3939,
+      "step": 1800
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.4779504537582397,
+      "eval_runtime": 124.6728,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 1800
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 5.178096294403076,
+      "learning_rate": 3.8258514654266434e-05,
+      "loss": 1.5265,
+      "step": 1810
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 6.949739456176758,
+      "learning_rate": 3.813982973233083e-05,
+      "loss": 1.3674,
+      "step": 1820
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 3.84801983833313,
+      "learning_rate": 3.802073421344339e-05,
+      "loss": 1.4305,
+      "step": 1830
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 3.5803613662719727,
+      "learning_rate": 3.7901231819133105e-05,
+      "loss": 1.557,
+      "step": 1840
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 3.509099245071411,
+      "learning_rate": 3.7781326283643085e-05,
+      "loss": 1.3611,
+      "step": 1850
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 41.185279846191406,
+      "learning_rate": 3.766102135381393e-05,
+      "loss": 1.3944,
+      "step": 1860
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.797672748565674,
+      "learning_rate": 3.75403207889666e-05,
+      "loss": 1.2557,
+      "step": 1870
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 4.237602233886719,
+      "learning_rate": 3.741922836078499e-05,
+      "loss": 1.3583,
+      "step": 1880
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.5037312507629395,
+      "learning_rate": 3.729774785319801e-05,
+      "loss": 1.4619,
+      "step": 1890
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 4.292742729187012,
+      "learning_rate": 3.717588306226143e-05,
+      "loss": 1.3986,
+      "step": 1900
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 1.4685039520263672,
+      "eval_runtime": 124.7126,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 2.005,
+      "step": 1900
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.198277950286865,
+      "learning_rate": 3.705363779603917e-05,
+      "loss": 1.349,
+      "step": 1910
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 3.86722469329834,
+      "learning_rate": 3.693101587448436e-05,
+      "loss": 1.5053,
+      "step": 1920
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 8.68099594116211,
+      "learning_rate": 3.680802112931996e-05,
+      "loss": 1.3899,
+      "step": 1930
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 3.8347198963165283,
+      "learning_rate": 3.6684657403919005e-05,
+      "loss": 1.4519,
+      "step": 1940
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 9.875212669372559,
+      "learning_rate": 3.6560928553184554e-05,
+      "loss": 1.4788,
+      "step": 1950
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 8.638535499572754,
+      "learning_rate": 3.6436838443429175e-05,
+      "loss": 1.3777,
+      "step": 1960
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 3.73545503616333,
+      "learning_rate": 3.631239095225417e-05,
+      "loss": 1.4962,
+      "step": 1970
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 8.485962867736816,
+      "learning_rate": 3.618758996842839e-05,
+      "loss": 1.4377,
+      "step": 1980
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 4.3264055252075195,
+      "learning_rate": 3.60624393917667e-05,
+      "loss": 1.5695,
+      "step": 1990
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 3.979128837585449,
+      "learning_rate": 3.5936943133008183e-05,
+      "loss": 1.2959,
+      "step": 2000
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 1.4598569869995117,
+      "eval_runtime": 124.8036,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 2000
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 7.0864338874816895,
+      "learning_rate": 3.581110511369384e-05,
+      "loss": 1.4301,
+      "step": 2010
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 4.597893714904785,
+      "learning_rate": 3.568492926604412e-05,
+      "loss": 1.2962,
+      "step": 2020
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 3.7413573265075684,
+      "learning_rate": 3.555841953283603e-05,
+      "loss": 1.3708,
+      "step": 2030
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 4.206364631652832,
+      "learning_rate": 3.5431579867279905e-05,
+      "loss": 1.4758,
+      "step": 2040
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 5.203850269317627,
+      "learning_rate": 3.530441423289591e-05,
+      "loss": 1.4563,
+      "step": 2050
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 3.0671565532684326,
+      "learning_rate": 3.517692660339018e-05,
+      "loss": 1.322,
+      "step": 2060
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 4.655951499938965,
+      "learning_rate": 3.504912096253061e-05,
+      "loss": 1.4868,
+      "step": 2070
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 3.5286195278167725,
+      "learning_rate": 3.492100130402242e-05,
+      "loss": 1.3379,
+      "step": 2080
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 3.526078701019287,
+      "learning_rate": 3.479257163138334e-05,
+      "loss": 1.4864,
+      "step": 2090
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 4.072696208953857,
+      "learning_rate": 3.4663835957818515e-05,
+      "loss": 1.4187,
+      "step": 2100
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 1.4545879364013672,
+      "eval_runtime": 124.6694,
+      "eval_samples_per_second": 8.021,
+      "eval_steps_per_second": 2.005,
+      "step": 2100
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 6.851144313812256,
+      "learning_rate": 3.453479830609505e-05,
+      "loss": 1.5079,
+      "step": 2110
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 3.958353042602539,
+      "learning_rate": 3.440546270841639e-05,
+      "loss": 1.3578,
+      "step": 2120
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 5.926538944244385,
+      "learning_rate": 3.427583320629626e-05,
+      "loss": 1.3127,
+      "step": 2130
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 6.969961643218994,
+      "learning_rate": 3.414591385043237e-05,
+      "loss": 1.4254,
+      "step": 2140
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 5.364356994628906,
+      "learning_rate": 3.401570870057989e-05,
+      "loss": 1.3755,
+      "step": 2150
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 6.824484825134277,
+      "learning_rate": 3.3885221825424537e-05,
+      "loss": 1.544,
+      "step": 2160
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 7.165542125701904,
+      "learning_rate": 3.375445730245546e-05,
+      "loss": 1.3792,
+      "step": 2170
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 5.511162757873535,
+      "learning_rate": 3.362341921783784e-05,
+      "loss": 1.3733,
+      "step": 2180
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 3.903485059738159,
+      "learning_rate": 3.349211166628515e-05,
+      "loss": 1.3905,
+      "step": 2190
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 7.315738677978516,
+      "learning_rate": 3.336053875093128e-05,
+      "loss": 1.3279,
+      "step": 2200
+    },
+    {
+      "epoch": 3.91,
+      "eval_loss": 1.4570436477661133,
+      "eval_runtime": 124.7476,
+      "eval_samples_per_second": 8.016,
+      "eval_steps_per_second": 2.004,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.714511502611841e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2200/training_args.bin b/checkpoint-2200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-2200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-300/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-300/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1eac524e71150fb686c857b3ecde8b9d60c55a7e
--- /dev/null
+++ b/checkpoint-300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62a8d28271ab68808ee44f71aa2b4f2dcc08dac87d51374fe444dde09e4ba73
+size 3695848
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6ee8e6e316a63ec5a00bf0bc1a7d81ad59028fef
--- /dev/null
+++ b/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b724a509912c69f119c06fa3b99c6bc7e4feaad1af0d525b2d8636ab5c1df84
+size 7433594
diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c3cd38d64e5d7c3a674069e9029d353f1f2a9639
--- /dev/null
+++ b/checkpoint-300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91b4ea1ac4122d75cee55ecf1437282eb9805106878d0036e55b683f7e445d7
+size 14244
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4b7435ee8a97a7b70807fd2523a70ed9ce2ecbca
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8175ddae8fb9e4cb48cfee8d71a165eafcac69c750c31f6222ec6ff2ad52eacb
+size 1064
diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-300/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-300/tokenizer.model b/checkpoint-300/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-300/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-300/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..290a130b25513b4cb72814b1c2b7e84aedcb8ced
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,255 @@
+{
+  "best_metric": 1.7350378036499023,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-300",
+  "epoch": 0.5333333333333333,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 2.3293542877220045e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-400/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-400/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2bee83805c9cb1bef35d80ca26ca65206d91cdb5
--- /dev/null
+++ b/checkpoint-400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab271a4b70a5c35c29d5fb695355d2e3b920f7b05098071de97f7ef6d9855a8
+size 3695848
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..599f07d920d574ace9c503363a3f61f1d1656144
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0fc3086d5e2016399f03fcb7c65f3a04e0e302f677254d801505f38c726d52
+size 7433594
diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb825955c7b6f4d1916a925b98dd80e4a9b21daf
--- /dev/null
+++ b/checkpoint-400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d3cbca4c3fd3552f9312d9c0b0118f85c1d03a64923a22ccb32945c38a1de3
+size 14244
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..657c0ae6e493b810cd9ffb38058b26c3f9e5dbd8
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8e7f2a2b05604957d96a1a4c87d00ccd9fbbe98833f40440a985146176688b
+size 1064
diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-400/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-400/tokenizer.model b/checkpoint-400/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-400/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-400/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c28baafebe04a60284ae71eb06353f8a2eaadf6b
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,333 @@
+{
+  "best_metric": 1.6840696334838867,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-400",
+  "epoch": 0.7111111111111111,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 3.103976541168599e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-500/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-500/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..af01df7433c902621b6eabe1bb9f27ad72728df5
--- /dev/null
+++ b/checkpoint-500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a52ba5043422f3484785817facbbc0ae6be05c9bf53fdaca9723495ef5a1535
+size 3695848
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d4639645ff0f2cbff8c8a76a7c22278b4d4d9565
--- /dev/null
+++ b/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b70b4f8532779697ca80bf262658a8b18802dd4f451d5ea1399caccf6545c81
+size 7433594
diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..74e05692af8f6b030acb27251818991b0f73c563
--- /dev/null
+++ b/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52731161244c121a3b62356a5e8bf0f8cc2e15fefd2cd720673b8ae854a4ccf5
+size 14244
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d067ef917e5fe0dba941a255af54f14e7391263b
--- /dev/null
+++ b/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a57e18fb18db14878b8a155e12ea4b0ffa8b708eab5a5e3b3010da34e109ee
+size 1064
diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-500/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-500/tokenizer.model b/checkpoint-500/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-500/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-500/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9732139d797460906e649392f8561201d1655895
--- /dev/null
+++ b/checkpoint-500/trainer_state.json
@@ -0,0 +1,411 @@
+{
+  "best_metric": 1.6494970321655273,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-500",
+  "epoch": 0.8888888888888888,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 3.900024219508408e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-600/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-600/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6a65599373aefc016cea66fb3a4e85a7aaab2b03
--- /dev/null
+++ b/checkpoint-600/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3694054c6a2131e54f6caf4b2c0e27ae1a3c2b535cf180bb934e5b32cffaf3
+size 3695848
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..332c49ff96e7a94dd30c43b70164ba72b95efb73
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8159c9c508d0ef1f0b6bca3438b8ea65456ce1188997bb18e689b9ee29f17e1d
+size 7433594
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cace1b1f61a0e508e2d18b1f78140ffcf2c0aa17
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08175c45b878379b425d20603ff8117b6914cf3fa61640e2e083737ac207a756
+size 14244
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de80603803404cc8c6a8a259cfa6e7cee7e31963
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6532af35d88fbf684b13484cb01697ea6ea2a722c45a22fe3bcaa3a376d99541
+size 1064
diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-600/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-600/tokenizer.model b/checkpoint-600/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-600/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-600/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..454317f8cdc695a9ab26192b562dced727f19145
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,489 @@
+{
+  "best_metric": 1.6121476888656616,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-600",
+  "epoch": 1.0666666666666667,
+  "eval_steps": 100,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 4.721237505878262e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-700/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-700/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-700/adapter_model.safetensors b/checkpoint-700/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d3ef5564f72f99dc5f25f8aba9ac8611d46915e6
--- /dev/null
+++ b/checkpoint-700/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f379a39138a824d1913075128eebd0f886157f78aa4e236d8e844b2c99c87a8
+size 3695848
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9de044b9d8067aadfc9def06bba341babf4ac85c
--- /dev/null
+++ b/checkpoint-700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f5f27581f89051d59d7296a395fe7508f965b9a67d2371530cd2f70b2b3155
+size 7433594
diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bfcfe87cf506e8b7d471b048c4789bccdf54579c
--- /dev/null
+++ b/checkpoint-700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3374e4382848f81495cebce1074c1d945df4b41896ba0064e25dee533589aa42
+size 14244
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9c3c37237c39c2c1c406f6fa3fa578bbecf9cea9
--- /dev/null
+++ b/checkpoint-700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b77ac663dcaaf91a448ae8668c4d5946cd0cae79c85108863b5890d7b4b1a76
+size 1064
diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-700/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-700/tokenizer.model b/checkpoint-700/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-700/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-700/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0a57eea159da63de17fe5ba1c24c80c89ddf95af
--- /dev/null
+++ b/checkpoint-700/trainer_state.json
@@ -0,0 +1,567 @@
+{
+  "best_metric": 1.5970302820205688,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-700",
+  "epoch": 1.2444444444444445,
+  "eval_steps": 100,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 5.4696929182285824e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-800/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-800/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..faef3866440d2bc76614eaec75524cf6529adb5f
--- /dev/null
+++ b/checkpoint-800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb6fe1f205290e90a1b0d201ead217df8f3a6213df58a439af1854bfbcbb390
+size 3695848
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7f85aa4a90efef7f99dd43a73af7c86b5078996d
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663daa8b311e642a97e4d5564c1e1bc1fbc95702ab052d6860cdc621ab1d14d1
+size 7433594
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a26604bb05f029e8c445a2d7b4639f6a2ebd34ed
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84a4879b22d336e78e06b3337d056dda27b09f85240912d9f0bb7cd11e3be34
+size 14244
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3df93f3bb8f515740934b0599e7bf93799506ba9
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb6260e0865cd6fd54f15a4c3ca863963507aa707d0b43c4907093999453f25
+size 1064
diff --git a/checkpoint-800/special_tokens_map.json b/checkpoint-800/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-800/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-800/tokenizer.model b/checkpoint-800/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-800/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-800/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b26641d4cd027204ea871b078a84786ac0636d47
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,645 @@
+{
+  "best_metric": 1.5639870166778564,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-800",
+  "epoch": 1.4222222222222223,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 6.264551632302244e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..1d1a367c446e3a5f9a585222f3bda62c8b677d2b
--- /dev/null
+++ b/checkpoint-900/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/checkpoint-900/adapter_config.json b/checkpoint-900/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6acfc8290c87b51d6dc715b6eab7cf151b0652fb
--- /dev/null
+++ b/checkpoint-900/adapter_config.json
@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "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/checkpoint-900/adapter_model.safetensors b/checkpoint-900/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..57d5d4ca9e5cb14f57bb44e11378c52b58860875
--- /dev/null
+++ b/checkpoint-900/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4009e77e0868b3fe29c9eca2dd493a8d2362c0f828115f5cba4a3d1c9853588e
+size 3695848
diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6873b372af0dde73829dbe74a750dd286ae6a554
--- /dev/null
+++ b/checkpoint-900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facfc39a156152327521e946dbf042307e946af7dcef94e6ae2ec430d3e5fef4
+size 7433594
diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c3ce56c7eb9ca092520c460db9e87c601284eb72
--- /dev/null
+++ b/checkpoint-900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e9a581ca85a141ade05a3dc7e0010c5a1cb23bfe7f026419952e74bb6df42d
+size 14244
diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d6f42f81266d7af99c1174c3f52e283997fd064e
--- /dev/null
+++ b/checkpoint-900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9cbba91548afe366b31f98f77877763ec337b14ec80fd4d1b111caad3b7936
+size 1064
diff --git a/checkpoint-900/special_tokens_map.json b/checkpoint-900/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6119589e367b2de0fc8cbd2f1217667532e3174
--- /dev/null
+++ b/checkpoint-900/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-900/tokenizer.model b/checkpoint-900/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/checkpoint-900/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/checkpoint-900/tokenizer_config.json b/checkpoint-900/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f08ad0abe7fe305103ce90b38e6f11a84d917681
--- /dev/null
+++ b/checkpoint-900/tokenizer_config.json
@@ -0,0 +1,51 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..615e80baee5bb4949e642e242db434802c825c0b
--- /dev/null
+++ b/checkpoint-900/trainer_state.json
@@ -0,0 +1,723 @@
+{
+  "best_metric": 1.5639870166778564,
+  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-800",
+  "epoch": 1.6,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.6079277992248535,
+      "learning_rate": 4.999960939662063e-05,
+      "loss": 3.747,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.2283411026000977,
+      "learning_rate": 4.999843759868819e-05,
+      "loss": 3.5789,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 41.573001861572266,
+      "learning_rate": 4.999648464281934e-05,
+      "loss": 3.1683,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.080965518951416,
+      "learning_rate": 4.9993750590040575e-05,
+      "loss": 2.8275,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.576275825500488,
+      "learning_rate": 4.999023552578632e-05,
+      "loss": 2.6758,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 18.012842178344727,
+      "learning_rate": 4.998593955989626e-05,
+      "loss": 2.6287,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.738934516906738,
+      "learning_rate": 4.9980862826611875e-05,
+      "loss": 2.5284,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.353776216506958,
+      "learning_rate": 4.9975005484572305e-05,
+      "loss": 2.2608,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.6298699378967285,
+      "learning_rate": 4.9968367716809374e-05,
+      "loss": 2.2475,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 50.594207763671875,
+      "learning_rate": 4.996094973074183e-05,
+      "loss": 2.2007,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.126384735107422,
+      "eval_runtime": 124.9221,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.225520133972168,
+      "learning_rate": 4.995275175816891e-05,
+      "loss": 1.9414,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.777626991271973,
+      "learning_rate": 4.994377405526308e-05,
+      "loss": 1.9729,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.133576393127441,
+      "learning_rate": 4.993401690256203e-05,
+      "loss": 2.0237,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.396271228790283,
+      "learning_rate": 4.992348060495989e-05,
+      "loss": 2.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.4974453449249268,
+      "learning_rate": 4.991216549169776e-05,
+      "loss": 2.032,
+      "step": 150
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.256199836730957,
+      "learning_rate": 4.990007191635334e-05,
+      "loss": 1.9548,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.5634379386901855,
+      "learning_rate": 4.988720025682995e-05,
+      "loss": 1.8164,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.023727416992188,
+      "learning_rate": 4.987355091534468e-05,
+      "loss": 1.8517,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.622091293334961,
+      "learning_rate": 4.985912431841584e-05,
+      "loss": 2.0255,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9935083389282227,
+      "learning_rate": 4.9843920916849645e-05,
+      "loss": 1.8777,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.8619400262832642,
+      "eval_runtime": 124.8712,
+      "eval_samples_per_second": 8.008,
+      "eval_steps_per_second": 2.002,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.256485939025879,
+      "learning_rate": 4.982794118572609e-05,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.212824821472168,
+      "learning_rate": 4.981118562438414e-05,
+      "loss": 1.7744,
+      "step": 220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.2626118659973145,
+      "learning_rate": 4.9793654756406085e-05,
+      "loss": 1.7545,
+      "step": 230
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.217405796051025,
+      "learning_rate": 4.9775349129601243e-05,
+      "loss": 1.5633,
+      "step": 240
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 22.393404006958008,
+      "learning_rate": 4.9756269315988804e-05,
+      "loss": 1.8871,
+      "step": 250
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.6576473712921143,
+      "learning_rate": 4.973641591177991e-05,
+      "loss": 1.7037,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.2433271408081055,
+      "learning_rate": 4.971578953735912e-05,
+      "loss": 1.7631,
+      "step": 270
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7399721145629883,
+      "learning_rate": 4.969439083726496e-05,
+      "loss": 1.7714,
+      "step": 280
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.575680255889893,
+      "learning_rate": 4.967222048016979e-05,
+      "loss": 1.8699,
+      "step": 290
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 7.729683876037598,
+      "learning_rate": 4.964927915885893e-05,
+      "loss": 1.6566,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7350378036499023,
+      "eval_runtime": 124.9278,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.755899667739868,
+      "learning_rate": 4.962556759020898e-05,
+      "loss": 1.7193,
+      "step": 310
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.513024091720581,
+      "learning_rate": 4.960108651516545e-05,
+      "loss": 1.852,
+      "step": 320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.7794790267944336,
+      "learning_rate": 4.9575836698719605e-05,
+      "loss": 1.6785,
+      "step": 330
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.2256739139556885,
+      "learning_rate": 4.954981892988451e-05,
+      "loss": 1.6648,
+      "step": 340
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8756954669952393,
+      "learning_rate": 4.952303402167047e-05,
+      "loss": 1.6399,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.057961463928223,
+      "learning_rate": 4.949548281105951e-05,
+      "loss": 1.5875,
+      "step": 360
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.63081169128418,
+      "learning_rate": 4.946716615897932e-05,
+      "loss": 1.6708,
+      "step": 370
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.755204200744629,
+      "learning_rate": 4.943808495027631e-05,
+      "loss": 1.636,
+      "step": 380
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.21866226196289,
+      "learning_rate": 4.940824009368793e-05,
+      "loss": 1.5714,
+      "step": 390
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.44133186340332,
+      "learning_rate": 4.937763252181434e-05,
+      "loss": 1.4084,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.6840696334838867,
+      "eval_runtime": 124.8851,
+      "eval_samples_per_second": 8.007,
+      "eval_steps_per_second": 2.002,
+      "step": 400
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.056345224380493,
+      "learning_rate": 4.934626319108923e-05,
+      "loss": 1.7233,
+      "step": 410
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.303133487701416,
+      "learning_rate": 4.93141330817499e-05,
+      "loss": 1.5374,
+      "step": 420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.2246623039245605,
+      "learning_rate": 4.9281243197806726e-05,
+      "loss": 1.8547,
+      "step": 430
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.8070685863494873,
+      "learning_rate": 4.924759456701167e-05,
+      "loss": 1.5721,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.243337392807007,
+      "learning_rate": 4.9213188240826245e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.166132926940918,
+      "learning_rate": 4.917802529438864e-05,
+      "loss": 1.6621,
+      "step": 460
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.54414701461792,
+      "learning_rate": 4.9142106826480114e-05,
+      "loss": 1.6088,
+      "step": 470
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 9.983458518981934,
+      "learning_rate": 4.910543395949067e-05,
+      "loss": 1.6152,
+      "step": 480
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 6.45111608505249,
+      "learning_rate": 4.9068007839383946e-05,
+      "loss": 1.6361,
+      "step": 490
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 108.82310485839844,
+      "learning_rate": 4.9029829635661475e-05,
+      "loss": 1.7045,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.6494970321655273,
+      "eval_runtime": 124.6904,
+      "eval_samples_per_second": 8.02,
+      "eval_steps_per_second": 2.005,
+      "step": 500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.705786228179932,
+      "learning_rate": 4.899090054132609e-05,
+      "loss": 1.738,
+      "step": 510
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.800131320953369,
+      "learning_rate": 4.895122177284465e-05,
+      "loss": 1.6218,
+      "step": 520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.11057186126709,
+      "learning_rate": 4.891079457011005e-05,
+      "loss": 1.5169,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.329095840454102,
+      "learning_rate": 4.8869620196402436e-05,
+      "loss": 1.7979,
+      "step": 540
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.9115641117095947,
+      "learning_rate": 4.882769993834978e-05,
+      "loss": 1.7073,
+      "step": 550
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.80266809463501,
+      "learning_rate": 4.878503510588765e-05,
+      "loss": 1.6541,
+      "step": 560
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 9.07653522491455,
+      "learning_rate": 4.874162703221823e-05,
+      "loss": 1.6888,
+      "step": 570
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.492751598358154,
+      "learning_rate": 4.8697477073768766e-05,
+      "loss": 1.6448,
+      "step": 580
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.852599143981934,
+      "learning_rate": 4.8652586610149095e-05,
+      "loss": 1.6236,
+      "step": 590
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 5.424524307250977,
+      "learning_rate": 4.8606957044108556e-05,
+      "loss": 1.4969,
+      "step": 600
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.6121476888656616,
+      "eval_runtime": 124.7413,
+      "eval_samples_per_second": 8.017,
+      "eval_steps_per_second": 2.004,
+      "step": 600
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 3.611617088317871,
+      "learning_rate": 4.856058980149216e-05,
+      "loss": 1.4571,
+      "step": 610
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.210519313812256,
+      "learning_rate": 4.851348633119606e-05,
+      "loss": 1.63,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 95.43629455566406,
+      "learning_rate": 4.84656481051222e-05,
+      "loss": 1.6034,
+      "step": 630
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 4.3693528175354,
+      "learning_rate": 4.8417076618132426e-05,
+      "loss": 1.5791,
+      "step": 640
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.691178321838379,
+      "learning_rate": 4.836777338800168e-05,
+      "loss": 1.5327,
+      "step": 650
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.547637939453125,
+      "learning_rate": 4.8317739955370636e-05,
+      "loss": 1.4278,
+      "step": 660
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.426717519760132,
+      "learning_rate": 4.8266977883697515e-05,
+      "loss": 1.5317,
+      "step": 670
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.004473924636841,
+      "learning_rate": 4.821548875920927e-05,
+      "loss": 1.6848,
+      "step": 680
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.686044931411743,
+      "learning_rate": 4.816327419085196e-05,
+      "loss": 1.6079,
+      "step": 690
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.130298137664795,
+      "learning_rate": 4.811033581024056e-05,
+      "loss": 1.5998,
+      "step": 700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5970302820205688,
+      "eval_runtime": 124.9388,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 2.001,
+      "step": 700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 6.1143059730529785,
+      "learning_rate": 4.805667527160788e-05,
+      "loss": 1.554,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 31.27813148498535,
+      "learning_rate": 4.800229425175294e-05,
+      "loss": 1.5824,
+      "step": 720
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 9.035768508911133,
+      "learning_rate": 4.7947194449988555e-05,
+      "loss": 1.547,
+      "step": 730
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 39.38993835449219,
+      "learning_rate": 4.7891377588088223e-05,
+      "loss": 1.5795,
+      "step": 740
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 7.738800048828125,
+      "learning_rate": 4.7834845410232356e-05,
+      "loss": 1.5761,
+      "step": 750
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.3933961391448975,
+      "learning_rate": 4.777759968295369e-05,
+      "loss": 1.6293,
+      "step": 760
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 4.511744022369385,
+      "learning_rate": 4.771964219508222e-05,
+      "loss": 1.4761,
+      "step": 770
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.566397190093994,
+      "learning_rate": 4.766097475768919e-05,
+      "loss": 1.5707,
+      "step": 780
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.365654945373535,
+      "learning_rate": 4.7601599204030544e-05,
+      "loss": 1.3932,
+      "step": 790
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.3254847526550293,
+      "learning_rate": 4.754151738948962e-05,
+      "loss": 1.6041,
+      "step": 800
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.5639870166778564,
+      "eval_runtime": 124.923,
+      "eval_samples_per_second": 8.005,
+      "eval_steps_per_second": 2.001,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.520264148712158,
+      "learning_rate": 4.7480731191519224e-05,
+      "loss": 1.4991,
+      "step": 810
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 5.3987531661987305,
+      "learning_rate": 4.741924250958289e-05,
+      "loss": 1.6856,
+      "step": 820
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 12.352794647216797,
+      "learning_rate": 4.7357053265095575e-05,
+      "loss": 1.4509,
+      "step": 830
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 9.825531005859375,
+      "learning_rate": 4.729416540136361e-05,
+      "loss": 1.6168,
+      "step": 840
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 10.881526947021484,
+      "learning_rate": 4.723058088352395e-05,
+      "loss": 1.5783,
+      "step": 850
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 6.232407093048096,
+      "learning_rate": 4.7166301698482815e-05,
+      "loss": 1.4556,
+      "step": 860
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.3216302394866943,
+      "learning_rate": 4.710132985485355e-05,
+      "loss": 1.593,
+      "step": 870
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 5.219264984130859,
+      "learning_rate": 4.703566738289389e-05,
+      "loss": 1.5131,
+      "step": 880
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 7.875769138336182,
+      "learning_rate": 4.696931633444251e-05,
+      "loss": 1.5667,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.77959680557251,
+      "learning_rate": 4.69022787828549e-05,
+      "loss": 1.5211,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.5731443166732788,
+      "eval_runtime": 124.8025,
+      "eval_samples_per_second": 8.013,
+      "eval_steps_per_second": 2.003,
+      "step": 900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7.080392918182134e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f141004eacb993ed2644ad1df0d132a6a81d8
--- /dev/null
+++ b/checkpoint-900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3882dfa1e7d13fcab0815293b9ac841a1a275771a1fdadce3f013196b52e019b
+size 5048
diff --git a/runs/.DS_Store b/runs/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..8afaa88626997669157da5e19b44fcf5718e3b5a
Binary files /dev/null and b/runs/.DS_Store differ
diff --git a/runs/events.out.tfevents.1709267884.cca2c738afde b/runs/events.out.tfevents.1709267884.cca2c738afde
new file mode 100644
index 0000000000000000000000000000000000000000..a96834e25b6e250c36a2b4a3e5ba7bfd4b070c11
--- /dev/null
+++ b/runs/events.out.tfevents.1709267884.cca2c738afde
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e56c2ec018bb543cc1d5215c48ac5d5ad5d95b670c099eeab972d04eed30268
+size 57768