diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..9a2a24b8d75387978f08e71fadfecc35f48d6265 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mistral-finetune filter=lfs diff=lfs merge=lfs -text
diff --git a/mistral-finetune/checkpoint-10/README.md b/mistral-finetune/checkpoint-10/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-10/adapter_config.json b/mistral-finetune/checkpoint-10/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-10/adapter_model.safetensors b/mistral-finetune/checkpoint-10/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..21b507053b3dd103b3dc826bb55dc64446f1227d
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c63d4ef034dce4230fe2889badf30ad55cee5ba9e385d1110ff7d2f35b5f7e0
+size 340225224
diff --git a/mistral-finetune/checkpoint-10/optimizer.pt b/mistral-finetune/checkpoint-10/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e323ba41ac560d9dd2b9d4693007dda20be34570
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df68c3f6f11c9a0cc120521d605201a11d52103ddb67e67caf50ebe524a4f151
+size 170951068
diff --git a/mistral-finetune/checkpoint-10/rng_state.pth b/mistral-finetune/checkpoint-10/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..52bee0693c9bb8d7f6b94ac3e6ec4278391d36fc
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b61f55cfd4c21c97ef9c110d90f7c3b398be35ef6c0cee4ee24bf0940d369c2
+size 14244
diff --git a/mistral-finetune/checkpoint-10/scheduler.pt b/mistral-finetune/checkpoint-10/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4733ccf58143bf4090c346e587f5685d4153bfb9
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70520427b653bb8423e280b7d7c2fe058746573b9bc95b7b9a1d6434d294f84
+size 1064
diff --git a/mistral-finetune/checkpoint-10/trainer_state.json b/mistral-finetune/checkpoint-10/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..198c9dc499d530520e905bb37fdc0d2714a8696d
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/trainer_state.json
@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.025,
+  "eval_steps": 10,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1726968299520000.0,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-10/training_args.bin b/mistral-finetune/checkpoint-10/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-10/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-100/README.md b/mistral-finetune/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-100/adapter_config.json b/mistral-finetune/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-100/adapter_model.safetensors b/mistral-finetune/checkpoint-100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..050feca93209580884f6783daaeae75af9f38465
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af310d5cf3b1351634e4e0b1f060023d3002be79a937fa5d0262942504088170
+size 340225224
diff --git a/mistral-finetune/checkpoint-100/optimizer.pt b/mistral-finetune/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3f65cd51a2a66ccfb16bbcde18d2b7b99d2deb70
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db707e2ce9e6b240070f57c268f24aee523e03a159383bff52ab4e270e17587
+size 170951068
diff --git a/mistral-finetune/checkpoint-100/rng_state.pth b/mistral-finetune/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6720213ecbbb3d782f21adbd53ce6a81938b1b8e
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb35848be78a9672c2de9c9ea1cb1d4557f79a6caf73eb10ba23b4d7bd8a3fe
+size 14244
diff --git a/mistral-finetune/checkpoint-100/scheduler.pt b/mistral-finetune/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a6d95fed89a165c6908cece326a09ec9e8246ea6
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223c492754e7d0cc7c6aeaee1fe7206a93415033615b3379f11649bd0f09644e
+size 1064
diff --git a/mistral-finetune/checkpoint-100/trainer_state.json b/mistral-finetune/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d53891c5ff1c23d1a92527c16853e782fc3ef2ba
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/trainer_state.json
@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "eval_steps": 10,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.72696829952e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-100/training_args.bin b/mistral-finetune/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-110/README.md b/mistral-finetune/checkpoint-110/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-110/adapter_config.json b/mistral-finetune/checkpoint-110/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-110/adapter_model.safetensors b/mistral-finetune/checkpoint-110/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7f0a8895d0036361e813f0a7a109634621c8561d
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a4a154192e76123afaf4cc8d24337b1a065618eedf4fbf61ca1797ecb2c4dd
+size 340225224
diff --git a/mistral-finetune/checkpoint-110/optimizer.pt b/mistral-finetune/checkpoint-110/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..10566d30a3e19759b432914bc50cfb5295d2cd74
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed59d79d82c25eba858eaf972b9148fc76e7a8c938933c444dcc4146edb66e3c
+size 170951068
diff --git a/mistral-finetune/checkpoint-110/rng_state.pth b/mistral-finetune/checkpoint-110/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49eab3de52a3569eedc58e11b302bb59b0451df7
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de951edb99ec057e0535ef0ec8bb69b7c53da2e3e5d9da128bd471689d04a492
+size 14244
diff --git a/mistral-finetune/checkpoint-110/scheduler.pt b/mistral-finetune/checkpoint-110/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2326fbf008e4af392cd12f6e5d937e2f1b7f6730
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98376fc2f0573046cc61f0f7d3d2abb920e8da027d876164c598937cdba2225
+size 1064
diff --git a/mistral-finetune/checkpoint-110/trainer_state.json b/mistral-finetune/checkpoint-110/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..74e3cf23ac7161ca3e8c8d29aa75621df7515738
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/trainer_state.json
@@ -0,0 +1,174 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.275,
+  "eval_steps": 10,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9539078156312626e-05,
+      "loss": 1.4684,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.4176369905471802,
+      "eval_runtime": 221.7309,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.899665129472e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-110/training_args.bin b/mistral-finetune/checkpoint-110/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-110/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-120/README.md b/mistral-finetune/checkpoint-120/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-120/adapter_config.json b/mistral-finetune/checkpoint-120/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-120/adapter_model.safetensors b/mistral-finetune/checkpoint-120/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e273afac9c2e39d3b5bb2eac64629988a40db395
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304b78450733e7f3ebcfb1e54c544d2cffa6f9f4ed2c760b70beda2fe4db5315
+size 340225224
diff --git a/mistral-finetune/checkpoint-120/optimizer.pt b/mistral-finetune/checkpoint-120/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..41967bf4b80343c9b339e1000ca2e12513950bcf
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4fdaa9307c3654b770d22104b0603837a78c7f2b872c3ffdf0973e4bfa3234
+size 170951068
diff --git a/mistral-finetune/checkpoint-120/rng_state.pth b/mistral-finetune/checkpoint-120/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c20308fda3786609b2ac880f26b4008280bdfaca
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3785253b2a2cd1c32045ff55ab786308b69aa6389827f0371daf27f9e5310394
+size 14244
diff --git a/mistral-finetune/checkpoint-120/scheduler.pt b/mistral-finetune/checkpoint-120/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8834925568d500e88cf08936aa8e94e9c40e2da6
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9791fab4c3a763dba5281d6ca071c917b80084acdd9a02fabb44788c90d8f4b
+size 1064
diff --git a/mistral-finetune/checkpoint-120/trainer_state.json b/mistral-finetune/checkpoint-120/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1e911868c5a32ba0266f93a501247e7c9b62f8bf
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/trainer_state.json
@@ -0,0 +1,188 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3,
+  "eval_steps": 10,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9539078156312626e-05,
+      "loss": 1.4684,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.4176369905471802,
+      "eval_runtime": 221.7309,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.903807615230461e-05,
+      "loss": 1.2462,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.4165884256362915,
+      "eval_runtime": 221.7346,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 2.072361959424e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-120/training_args.bin b/mistral-finetune/checkpoint-120/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-120/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-20/README.md b/mistral-finetune/checkpoint-20/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-20/adapter_config.json b/mistral-finetune/checkpoint-20/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-20/adapter_model.safetensors b/mistral-finetune/checkpoint-20/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..89f7dbd62a2ead4bf47133824c2daab4f1cbcc29
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8ea207882ba8096c212ea65254f666345a895ad5518a92200e633d853650ac
+size 340225224
diff --git a/mistral-finetune/checkpoint-20/optimizer.pt b/mistral-finetune/checkpoint-20/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7fe1d605ae071f401f0f5551a4e592c1b606b89e
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0086171fbd835609a4716345d0f75122fbeed52d410553a73fd35457f1b3ddff
+size 170951068
diff --git a/mistral-finetune/checkpoint-20/rng_state.pth b/mistral-finetune/checkpoint-20/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..19f16e77556fadd9765d059ec80c5e182870b593
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2418da8f729fea94d8af00ab12b2b4d7369a07a94da147759498d89b5d74f6ce
+size 14244
diff --git a/mistral-finetune/checkpoint-20/scheduler.pt b/mistral-finetune/checkpoint-20/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..974d321305ce8a10d5f8ba503847cefbeb9519fe
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9aa8d6b210f5857d64e00d2d5b5bf8d1606b011a7810b84dbbb874aedd0d56e
+size 1064
diff --git a/mistral-finetune/checkpoint-20/trainer_state.json b/mistral-finetune/checkpoint-20/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..72866a6a3ecd51139b76d6392589e914fd6b978b
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/trainer_state.json
@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05,
+  "eval_steps": 10,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 3453936599040000.0,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-20/training_args.bin b/mistral-finetune/checkpoint-20/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-20/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-30/README.md b/mistral-finetune/checkpoint-30/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-30/adapter_config.json b/mistral-finetune/checkpoint-30/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-30/adapter_model.safetensors b/mistral-finetune/checkpoint-30/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..950eb761c96d5b9bbf0c42adae41941bb828f879
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20f7e366d48ae58f58911c8a8b1a34de310010037a1dc3f15e481b77a9b78dc
+size 340225224
diff --git a/mistral-finetune/checkpoint-30/optimizer.pt b/mistral-finetune/checkpoint-30/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d11ff494d20df33c74172e635beceb1bbeb207de
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d78cae13032442b0c5f29a7138cc9f6cc8ca89798ad01096f50dc49163b0740
+size 170951068
diff --git a/mistral-finetune/checkpoint-30/rng_state.pth b/mistral-finetune/checkpoint-30/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..588e5e3be2699a9cc202bf6369407d4c486425c6
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a381c2e890979e6338e01c3198be40d18103ef1cf97f05c682cfd1dc6ee504
+size 14244
diff --git a/mistral-finetune/checkpoint-30/scheduler.pt b/mistral-finetune/checkpoint-30/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de1158489295b1bef5eb4a2a36c7ac2955546818
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e32004f632ac46e32797254a8bbdba4c1bc2a634bf0de930a2f2c3db5631a8f
+size 1064
diff --git a/mistral-finetune/checkpoint-30/trainer_state.json b/mistral-finetune/checkpoint-30/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fd5b7e4b8ab2e5713cb80ba0bebae92492a9617f
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/trainer_state.json
@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.075,
+  "eval_steps": 10,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 5180904898560000.0,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-30/training_args.bin b/mistral-finetune/checkpoint-30/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-30/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-40/README.md b/mistral-finetune/checkpoint-40/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-40/adapter_config.json b/mistral-finetune/checkpoint-40/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-40/adapter_model.safetensors b/mistral-finetune/checkpoint-40/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a134a7aba13eaf9f3d64daf3cb0104b0a7162559
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed6ecbe39cb5f276d793e273d56f54f27f8b2ac2833a19df2b7df63141214e7
+size 340225224
diff --git a/mistral-finetune/checkpoint-40/optimizer.pt b/mistral-finetune/checkpoint-40/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5c0cadbd54f8789d6bddd2ab9a80f12fe3f65868
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9f914999cc732a9fcb1bcadce240962db0859d5cc932d6d33ae67775c628ea
+size 170951068
diff --git a/mistral-finetune/checkpoint-40/rng_state.pth b/mistral-finetune/checkpoint-40/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7061bc2a7d7735d19cde1c74f22ac4f1422e5e3a
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dea05c555677ff5f3968498c1b81f65ad76691d1329933bb7707362aca42db
+size 14244
diff --git a/mistral-finetune/checkpoint-40/scheduler.pt b/mistral-finetune/checkpoint-40/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cc4d7c98c176c7a8c06125625e92dfe8388df917
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c039a8f519d96e4b421a57045a315b49da3d8f215aea391dfe7d8bc5cfa815
+size 1064
diff --git a/mistral-finetune/checkpoint-40/trainer_state.json b/mistral-finetune/checkpoint-40/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd09c279bbbf910088ad1068fc6218c4fa1d80ab
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/trainer_state.json
@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 10,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 6907873198080000.0,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-40/training_args.bin b/mistral-finetune/checkpoint-40/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-40/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-50/README.md b/mistral-finetune/checkpoint-50/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-50/adapter_config.json b/mistral-finetune/checkpoint-50/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-50/adapter_model.safetensors b/mistral-finetune/checkpoint-50/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ab56d568bad0f52593e3b2e7ce1ee97ce5bff7d9
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5eccc53c67ff398d14bdd39b9b36c21a9c4561ec625c9290de40ac7e7fb93a
+size 340225224
diff --git a/mistral-finetune/checkpoint-50/optimizer.pt b/mistral-finetune/checkpoint-50/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac7bb0599cc0dd2c151f0996cd3d27a324934eee
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f67452527bcd5e5da004f9f13c1da8a76f2fb4a6b56ae435abe26bacebb5f24
+size 170951068
diff --git a/mistral-finetune/checkpoint-50/rng_state.pth b/mistral-finetune/checkpoint-50/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..347be1b0f273d1ea879637faae7d552511d52ec5
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f11f941970f1e1e461b3ec88d820d55b7f33a0bce61fa79e53209dbe5ee1de
+size 14244
diff --git a/mistral-finetune/checkpoint-50/scheduler.pt b/mistral-finetune/checkpoint-50/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d17f4be1faec4b8c6ee308aab60e6dd4e376f429
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd89bb2121046cc5aa6d1258905c621118891cc757ea10ac4915d56dd8065c1
+size 1064
diff --git a/mistral-finetune/checkpoint-50/trainer_state.json b/mistral-finetune/checkpoint-50/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1bf24419c2cfa38c4d3ca98fb13e0e9062b0e972
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/trainer_state.json
@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.125,
+  "eval_steps": 10,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 8634841497600000.0,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-50/training_args.bin b/mistral-finetune/checkpoint-50/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-50/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-60/README.md b/mistral-finetune/checkpoint-60/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-60/adapter_config.json b/mistral-finetune/checkpoint-60/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-60/adapter_model.safetensors b/mistral-finetune/checkpoint-60/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..21a323e68708bb711d2c6091ac5cb45536e16cf7
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db566c1036fc1db3d376c82b55843eb34d53eb9632c12f22ac41e78a87ad3e5
+size 340225224
diff --git a/mistral-finetune/checkpoint-60/optimizer.pt b/mistral-finetune/checkpoint-60/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e4a862f96c7fd0621bc510400154e548532310f
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd01da7eb33753931f6c3d92f9ee9099c595d1657ef1ea730a2c3fb54f39e33b
+size 170951068
diff --git a/mistral-finetune/checkpoint-60/rng_state.pth b/mistral-finetune/checkpoint-60/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9b54ac73c9cc86ad9881ed217a3d852c3672a75d
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba767d98ae9ae7f9e6972ed5f1768f6cbe304f371c52598512c147a5a23b433
+size 14244
diff --git a/mistral-finetune/checkpoint-60/scheduler.pt b/mistral-finetune/checkpoint-60/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bd8a749b1091fbdbf1424913a4ec10e89326e6e2
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277afc1edb86556012dbf95c79a367ff3feca280fa704581a0f46fae7be53cee
+size 1064
diff --git a/mistral-finetune/checkpoint-60/trainer_state.json b/mistral-finetune/checkpoint-60/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5765628e8fb413dae884dee10ee6e562a0ea2c47
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/trainer_state.json
@@ -0,0 +1,104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15,
+  "eval_steps": 10,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.036180979712e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-60/training_args.bin b/mistral-finetune/checkpoint-60/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-60/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-70/README.md b/mistral-finetune/checkpoint-70/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-70/adapter_config.json b/mistral-finetune/checkpoint-70/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-70/adapter_model.safetensors b/mistral-finetune/checkpoint-70/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e917479230778da78db0c39a2cd38b41176b8972
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efaf4c970d6aa64551a0873c937164c9eb102ba6091f50a6a79c9eaef404510
+size 340225224
diff --git a/mistral-finetune/checkpoint-70/optimizer.pt b/mistral-finetune/checkpoint-70/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fa07c320995277e47eab66076b45757ddb2fd8cb
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e8bc9ad30ff0c3137ace7858eda102d10641688ef7a4f4c67f75e138803a05
+size 170951068
diff --git a/mistral-finetune/checkpoint-70/rng_state.pth b/mistral-finetune/checkpoint-70/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4c3f9ce105d3ab6c1d7704781a92713c9210d8ea
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8df1f81169d34a7262980efbc2ef7e65533b29b3ba881d0d607812965692431
+size 14244
diff --git a/mistral-finetune/checkpoint-70/scheduler.pt b/mistral-finetune/checkpoint-70/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f8869840c3038c9546ce33d5a65d7130a02a13a0
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d789e81b1d27dfdfbacad9a1f6762dab8a52d1b12cd636d566e20fd2552b556
+size 1064
diff --git a/mistral-finetune/checkpoint-70/trainer_state.json b/mistral-finetune/checkpoint-70/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..80ced2536b488d30ed1d0995a6bc719b200c4650
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/trainer_state.json
@@ -0,0 +1,118 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.175,
+  "eval_steps": 10,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.208877809664e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-70/training_args.bin b/mistral-finetune/checkpoint-70/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-70/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-80/README.md b/mistral-finetune/checkpoint-80/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-80/adapter_config.json b/mistral-finetune/checkpoint-80/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-80/adapter_model.safetensors b/mistral-finetune/checkpoint-80/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..689f774a14e165554f4284cd451e6184ffb0bbc1
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e487912e158ef7024a69d3843f4e24b172078b421e2973fb7888b6b72e62e207
+size 340225224
diff --git a/mistral-finetune/checkpoint-80/optimizer.pt b/mistral-finetune/checkpoint-80/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04f31e354e0aedb507b8499d3c79fe9bc17dc6a8
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc3c91d8657d419ef1e741cbd2d93ba86cb11290ce09c1c7a632b73633a4cce
+size 170951068
diff --git a/mistral-finetune/checkpoint-80/rng_state.pth b/mistral-finetune/checkpoint-80/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f77beefff46e589d13dbe236d4eb82ee1a198455
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63555738033314ade68c9c72d9c201c85569f9c07d55e01b0b4b8b581f1b05fe
+size 14244
diff --git a/mistral-finetune/checkpoint-80/scheduler.pt b/mistral-finetune/checkpoint-80/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fb58ea0462b484914be3a7f53c666fadcb6a7170
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f700bca9e7b5da964ac97281b5c74245a25f4bc04155ddb700616f25fb1f6ab
+size 1064
diff --git a/mistral-finetune/checkpoint-80/trainer_state.json b/mistral-finetune/checkpoint-80/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b90c4a17ceb8dbc11f88724b38d1f308b44defd7
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/trainer_state.json
@@ -0,0 +1,132 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 10,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.381574639616e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-80/training_args.bin b/mistral-finetune/checkpoint-80/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-80/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600
diff --git a/mistral-finetune/checkpoint-90/README.md b/mistral-finetune/checkpoint-90/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..56e705ea479e6ccaff9cbf438f85ddcec903644c
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/README.md
@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.3.dev0
diff --git a/mistral-finetune/checkpoint-90/adapter_config.json b/mistral-finetune/checkpoint-90/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8852ddff327ff01c0f6cae6f1eac89181e3b3d07
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/mistral-finetune/checkpoint-90/adapter_model.safetensors b/mistral-finetune/checkpoint-90/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b0413515abf1d632d2f6a383b1cddd99a7913e69
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1193d8a2851ad4e06a1a483fc16b468240f0432f6c4f8474bcf96f357f7cda
+size 340225224
diff --git a/mistral-finetune/checkpoint-90/optimizer.pt b/mistral-finetune/checkpoint-90/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2c271141ff91a8cb5875ac34a695995217f35708
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef0017bc18aaaa3f364f6eab74d5de8036c8e5a7f7dbe4d4fc76f32e3938ae9
+size 170951068
diff --git a/mistral-finetune/checkpoint-90/rng_state.pth b/mistral-finetune/checkpoint-90/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3db7aeea4345656624f4929ad8fcb2458af1d3fd
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d26ce9c110e18d02f4dd706b9ea1414610cd60f5b2321e60e0cef7b9daaddc
+size 14244
diff --git a/mistral-finetune/checkpoint-90/scheduler.pt b/mistral-finetune/checkpoint-90/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50e574b4187618675d2f7ed30e635d2c609bc07c
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8223131d1fd04e86f1b89979d6e6853172ca9a0180c6356fbdab5e331a89725
+size 1064
diff --git a/mistral-finetune/checkpoint-90/trainer_state.json b/mistral-finetune/checkpoint-90/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..10dbf283559e26ce8dbdcc469091601cbb1995ca
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/trainer_state.json
@@ -0,0 +1,146 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.225,
+  "eval_steps": 10,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.554271469568e+16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/mistral-finetune/checkpoint-90/training_args.bin b/mistral-finetune/checkpoint-90/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b7cd8b93caaea5c19553398360a620d4a4b00ad
--- /dev/null
+++ b/mistral-finetune/checkpoint-90/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600