Upload folder using huggingface_hub

README.md

@@ -0,0 +1,167 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model_type: AutoModelForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: ./data/raw_format/tool_used_training.jsonl
+    type: sharegpt
+  - path: ./data/raw_format/tool_not_used_training.jsonl
+    type: sharegpt
+  - path: ./data/raw_format/no_tools_training.jsonl
+    type: sharegpt
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 16
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+# lora_target_modules:
+#   - gate_proj
+#   - down_proj
+#   - up_proj
+#   - q_proj
+#   - v_proj
+#   - k_proj
+#   - o_proj
+
+wandb_project: function-call
+wandb_name: mixtral-instruct-qlora-v1
+wandb_log_model: end
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.001
+adam_beta2: 0.95
+adam_epsilon: 0.00001
+max_grad_norm: 1.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+# loss_watchdog_threshold: 5.0
+# loss_watchdog_patience: 3
+
+warmup_steps: 10
+# evals_per_epoch: 20
+eval_steps: 0.1
+save_steps: 0.1
+eval_table_size:
+eval_max_new_tokens: 256
+# saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 1.0
+fsdp:
+fsdp_config:
+```
+
+</details><br>
+
+# text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4076
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9379        | 0.03  | 1    | 0.9217          |
+| 0.7334        | 0.1   | 3    | 0.6238          |
+| 0.503         | 0.21  | 6    | 0.5134          |
+| 0.4644        | 0.31  | 9    | 0.4586          |
+| 0.4636        | 0.41  | 12   | 0.4403          |
+| 0.41          | 0.51  | 15   | 0.4276          |
+| 0.4248        | 0.62  | 18   | 0.4189          |
+| 0.4094        | 0.72  | 21   | 0.4120          |
+| 0.3905        | 0.82  | 24   | 0.4094          |
+| 0.3828        | 0.92  | 27   | 0.4076          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0.dev0
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7e80aa784f55ea66ccc25f34eb4886b5be46e9690098e95b333c1fab8ce46c
+size 167934026

checkpoint-18/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-18/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbbb85da9aa82075843c55dbbc6ff274cad7b087408eceee87f5bdfd858f3514
+size 167832240

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e267cec62485f465898529a7f164e64d5c4da025f8cdd57c95f9ec9d45c2e8
+size 84575956

checkpoint-18/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca69af62e50de6376be1a47a8fae4836695b44622e37e6d73f3bdd9087fcaf3
+size 14512

checkpoint-18/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa93de1b0d2f258782230a4576df1f465738b685d4ee45927142ba7eb73490f
+size 14512

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff35aabfe316308cff5ac7b8a7652458cc13c0c9fb1ec5df43ff765bce0216d
+size 1064

checkpoint-18/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.41894882917404175,
+  "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive/checkpoint-18",
+  "epoch": 0.6153846153846154,
+  "eval_steps": 3,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 0.9379,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9217294454574585,
+      "eval_runtime": 21.8917,
+      "eval_samples_per_second": 34.259,
+      "eval_steps_per_second": 8.588,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8714,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.7334,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6237823963165283,
+      "eval_runtime": 22.2516,
+      "eval_samples_per_second": 33.705,
+      "eval_steps_per_second": 8.449,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004,
+      "loss": 0.6181,
+      "step": 4
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005,
+      "loss": 0.5345,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0006,
+      "loss": 0.503,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.5134392976760864,
+      "eval_runtime": 22.3048,
+      "eval_samples_per_second": 33.625,
+      "eval_steps_per_second": 8.429,
+      "step": 6
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0007,
+      "loss": 0.5106,
+      "step": 7
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008,
+      "loss": 0.4623,
+      "step": 8
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.4644,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.45862117409706116,
+      "eval_runtime": 22.3188,
+      "eval_samples_per_second": 33.604,
+      "eval_steps_per_second": 8.423,
+      "step": 9
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.001,
+      "loss": 0.4399,
+      "step": 10
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0009931806517013613,
+      "loss": 0.4356,
+      "step": 11
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0009729086208503173,
+      "loss": 0.4636,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.44031861424446106,
+      "eval_runtime": 22.3297,
+      "eval_samples_per_second": 33.588,
+      "eval_steps_per_second": 8.419,
+      "step": 12
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009397368756032445,
+      "loss": 0.4481,
+      "step": 13
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0008945702546981969,
+      "loss": 0.4278,
+      "step": 14
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0008386407858128706,
+      "loss": 0.41,
+      "step": 15
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.42758792638778687,
+      "eval_runtime": 22.324,
+      "eval_samples_per_second": 33.596,
+      "eval_steps_per_second": 8.421,
+      "step": 15
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0007734740790612135,
+      "loss": 0.3787,
+      "step": 16
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0007008477123264848,
+      "loss": 0.4467,
+      "step": 17
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0006227427435703996,
+      "loss": 0.4248,
+      "step": 18
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.41894882917404175,
+      "eval_runtime": 22.3349,
+      "eval_samples_per_second": 33.58,
+      "eval_steps_per_second": 8.417,
+      "step": 18
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "total_flos": 1.0125064781011354e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707a93794938938c2e025fd684f764555a83be1ceba0b8160cb126c25caccdb
+size 5560

checkpoint-21/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-21/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-21/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ef0838c5cc04fef91306a60917e7777c8902ce8b957b3f80824e3350288f95
+size 167832240

checkpoint-21/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0437f0eae7eb88161c40692d2c9357891ccff93ce3ec9c174b274e757f2b111
+size 84575956

checkpoint-21/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699f9cdf423e6030bf62a0edbc5a2bb9280462ce94640fd0ae4c6f5dd4910caf
+size 14512

checkpoint-21/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a35f5a1899f7f28c0b86d1c7093518030eab1412073de803346c39357cfd7d
+size 14512

checkpoint-21/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa05a82b0334a94eada2619ffcbbc182e78567e33747a6645f304c746388d83
+size 1064

checkpoint-21/trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": 0.41203784942626953,
+  "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive/checkpoint-21",
+  "epoch": 0.717948717948718,
+  "eval_steps": 3,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 0.9379,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9217294454574585,
+      "eval_runtime": 21.8917,
+      "eval_samples_per_second": 34.259,
+      "eval_steps_per_second": 8.588,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8714,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.7334,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6237823963165283,
+      "eval_runtime": 22.2516,
+      "eval_samples_per_second": 33.705,
+      "eval_steps_per_second": 8.449,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004,
+      "loss": 0.6181,
+      "step": 4
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005,
+      "loss": 0.5345,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0006,
+      "loss": 0.503,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.5134392976760864,
+      "eval_runtime": 22.3048,
+      "eval_samples_per_second": 33.625,
+      "eval_steps_per_second": 8.429,
+      "step": 6
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0007,
+      "loss": 0.5106,
+      "step": 7
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008,
+      "loss": 0.4623,
+      "step": 8
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.4644,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.45862117409706116,
+      "eval_runtime": 22.3188,
+      "eval_samples_per_second": 33.604,
+      "eval_steps_per_second": 8.423,
+      "step": 9
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.001,
+      "loss": 0.4399,
+      "step": 10
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0009931806517013613,
+      "loss": 0.4356,
+      "step": 11
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0009729086208503173,
+      "loss": 0.4636,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.44031861424446106,
+      "eval_runtime": 22.3297,
+      "eval_samples_per_second": 33.588,
+      "eval_steps_per_second": 8.419,
+      "step": 12
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009397368756032445,
+      "loss": 0.4481,
+      "step": 13
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0008945702546981969,
+      "loss": 0.4278,
+      "step": 14
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0008386407858128706,
+      "loss": 0.41,
+      "step": 15
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.42758792638778687,
+      "eval_runtime": 22.324,
+      "eval_samples_per_second": 33.596,
+      "eval_steps_per_second": 8.421,
+      "step": 15
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0007734740790612135,
+      "loss": 0.3787,
+      "step": 16
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0007008477123264848,
+      "loss": 0.4467,
+      "step": 17
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0006227427435703996,
+      "loss": 0.4248,
+      "step": 18
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.41894882917404175,
+      "eval_runtime": 22.3349,
+      "eval_samples_per_second": 33.58,
+      "eval_steps_per_second": 8.417,
+      "step": 18
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0005412896727361663,
+      "loss": 0.3963,
+      "step": 19
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0004587103272638339,
+      "loss": 0.4,
+      "step": 20
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00037725725642960046,
+      "loss": 0.4094,
+      "step": 21
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.41203784942626953,
+      "eval_runtime": 22.3351,
+      "eval_samples_per_second": 33.579,
+      "eval_steps_per_second": 8.417,
+      "step": 21
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "total_flos": 1.181257557784658e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707a93794938938c2e025fd684f764555a83be1ceba0b8160cb126c25caccdb
+size 5560

checkpoint-24/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-24/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-24/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab584b315a7f25b79ad70cf7bd67914e35d2f8a17a273752b2919716a190889
+size 167832240

checkpoint-24/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e7ec50b76e94787a0ddbf0bebd8de2cd57ab4eda803edb6906698a779ce040
+size 84575956

checkpoint-24/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783936b6b8aface5c246b88e3bae5b4757a645279b23d5817f6d9e558a8995fc
+size 14512

checkpoint-24/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dded36ca1fd89396707f573e530d8becfaa0f5c81e2f5a9ba8d7aa2ca6137da4
+size 14512

checkpoint-24/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad8ca5a96573f8a8fc48641622c34e573d8d7717f30735698da3acc288156af
+size 1064

checkpoint-24/trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": 0.4093799591064453,
+  "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive/checkpoint-24",
+  "epoch": 0.8205128205128205,
+  "eval_steps": 3,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 0.9379,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9217294454574585,
+      "eval_runtime": 21.8917,
+      "eval_samples_per_second": 34.259,
+      "eval_steps_per_second": 8.588,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8714,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.7334,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6237823963165283,
+      "eval_runtime": 22.2516,
+      "eval_samples_per_second": 33.705,
+      "eval_steps_per_second": 8.449,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004,
+      "loss": 0.6181,
+      "step": 4
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005,
+      "loss": 0.5345,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0006,
+      "loss": 0.503,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.5134392976760864,
+      "eval_runtime": 22.3048,
+      "eval_samples_per_second": 33.625,
+      "eval_steps_per_second": 8.429,
+      "step": 6
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0007,
+      "loss": 0.5106,
+      "step": 7
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008,
+      "loss": 0.4623,
+      "step": 8
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.4644,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.45862117409706116,
+      "eval_runtime": 22.3188,
+      "eval_samples_per_second": 33.604,
+      "eval_steps_per_second": 8.423,
+      "step": 9
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.001,
+      "loss": 0.4399,
+      "step": 10
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0009931806517013613,
+      "loss": 0.4356,
+      "step": 11
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0009729086208503173,
+      "loss": 0.4636,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.44031861424446106,
+      "eval_runtime": 22.3297,
+      "eval_samples_per_second": 33.588,
+      "eval_steps_per_second": 8.419,
+      "step": 12
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009397368756032445,
+      "loss": 0.4481,
+      "step": 13
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0008945702546981969,
+      "loss": 0.4278,
+      "step": 14
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0008386407858128706,
+      "loss": 0.41,
+      "step": 15
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.42758792638778687,
+      "eval_runtime": 22.324,
+      "eval_samples_per_second": 33.596,
+      "eval_steps_per_second": 8.421,
+      "step": 15
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0007734740790612135,
+      "loss": 0.3787,
+      "step": 16
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0007008477123264848,
+      "loss": 0.4467,
+      "step": 17
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0006227427435703996,
+      "loss": 0.4248,
+      "step": 18
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.41894882917404175,
+      "eval_runtime": 22.3349,
+      "eval_samples_per_second": 33.58,
+      "eval_steps_per_second": 8.417,
+      "step": 18
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0005412896727361663,
+      "loss": 0.3963,
+      "step": 19
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0004587103272638339,
+      "loss": 0.4,
+      "step": 20
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00037725725642960046,
+      "loss": 0.4094,
+      "step": 21
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.41203784942626953,
+      "eval_runtime": 22.3351,
+      "eval_samples_per_second": 33.579,
+      "eval_steps_per_second": 8.417,
+      "step": 21
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002991522876735154,
+      "loss": 0.4013,
+      "step": 22
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00022652592093878665,
+      "loss": 0.3854,
+      "step": 23
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016135921418712956,
+      "loss": 0.3905,
+      "step": 24
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.4093799591064453,
+      "eval_runtime": 22.3288,
+      "eval_samples_per_second": 33.589,
+      "eval_steps_per_second": 8.42,
+      "step": 24
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "total_flos": 1.3500086374681805e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-24/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707a93794938938c2e025fd684f764555a83be1ceba0b8160cb126c25caccdb
+size 5560

checkpoint-27/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-27/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-27/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bd871f1d84e48470e9d1335e93cf36317698f34f09603eadef83012f573768
+size 167832240

checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e522fd438b89f6589d56a0f70068464eb6156fe9254df2bb78b2a40e7f0d2e
+size 84575956

checkpoint-27/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e7f0b6403d5cd8b94a0ad68ec5d993f2a464b655757c5568fd9319495dd4c4
+size 14512

checkpoint-27/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c0892a189161455e69e8313db9373b73814dac9003ff830d14004b14c0895f
+size 14512

checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82200edeb8acecbf8cac6e0a1a1ec36cc5f05f4710ee17935045027fb0d8c2d1
+size 1064

checkpoint-27/trainer_state.json

@@ -0,0 +1,263 @@
+{
+  "best_metric": 0.40758439898490906,
+  "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive/checkpoint-27",
+  "epoch": 0.9230769230769231,
+  "eval_steps": 3,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 0.9379,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9217294454574585,
+      "eval_runtime": 21.8917,
+      "eval_samples_per_second": 34.259,
+      "eval_steps_per_second": 8.588,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8714,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.7334,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6237823963165283,
+      "eval_runtime": 22.2516,
+      "eval_samples_per_second": 33.705,
+      "eval_steps_per_second": 8.449,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0004,
+      "loss": 0.6181,
+      "step": 4
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005,
+      "loss": 0.5345,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0006,
+      "loss": 0.503,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.5134392976760864,
+      "eval_runtime": 22.3048,
+      "eval_samples_per_second": 33.625,
+      "eval_steps_per_second": 8.429,
+      "step": 6
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0007,
+      "loss": 0.5106,
+      "step": 7
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008,
+      "loss": 0.4623,
+      "step": 8
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.4644,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.45862117409706116,
+      "eval_runtime": 22.3188,
+      "eval_samples_per_second": 33.604,
+      "eval_steps_per_second": 8.423,
+      "step": 9
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.001,
+      "loss": 0.4399,
+      "step": 10
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0009931806517013613,
+      "loss": 0.4356,
+      "step": 11
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0009729086208503173,
+      "loss": 0.4636,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.44031861424446106,
+      "eval_runtime": 22.3297,
+      "eval_samples_per_second": 33.588,
+      "eval_steps_per_second": 8.419,
+      "step": 12
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009397368756032445,
+      "loss": 0.4481,
+      "step": 13
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0008945702546981969,
+      "loss": 0.4278,
+      "step": 14
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0008386407858128706,
+      "loss": 0.41,
+      "step": 15
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.42758792638778687,
+      "eval_runtime": 22.324,
+      "eval_samples_per_second": 33.596,
+      "eval_steps_per_second": 8.421,
+      "step": 15
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0007734740790612135,
+      "loss": 0.3787,
+      "step": 16
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0007008477123264848,
+      "loss": 0.4467,
+      "step": 17
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0006227427435703996,
+      "loss": 0.4248,
+      "step": 18
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.41894882917404175,
+      "eval_runtime": 22.3349,
+      "eval_samples_per_second": 33.58,
+      "eval_steps_per_second": 8.417,
+      "step": 18
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0005412896727361663,
+      "loss": 0.3963,
+      "step": 19
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0004587103272638339,
+      "loss": 0.4,
+      "step": 20
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00037725725642960046,
+      "loss": 0.4094,
+      "step": 21
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.41203784942626953,
+      "eval_runtime": 22.3351,
+      "eval_samples_per_second": 33.579,
+      "eval_steps_per_second": 8.417,
+      "step": 21
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002991522876735154,
+      "loss": 0.4013,
+      "step": 22
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00022652592093878665,
+      "loss": 0.3854,
+      "step": 23
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016135921418712956,
+      "loss": 0.3905,
+      "step": 24
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.4093799591064453,
+      "eval_runtime": 22.3288,
+      "eval_samples_per_second": 33.589,
+      "eval_steps_per_second": 8.42,
+      "step": 24
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010542974530180327,
+      "loss": 0.3995,
+      "step": 25
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.026312439675552e-05,
+      "loss": 0.3992,
+      "step": 26
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.709137914968268e-05,
+      "loss": 0.3828,
+      "step": 27
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.40758439898490906,
+      "eval_runtime": 22.3234,
+      "eval_samples_per_second": 33.597,
+      "eval_steps_per_second": 8.422,
+      "step": 27
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "total_flos": 1.518759717151703e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707a93794938938c2e025fd684f764555a83be1ceba0b8160cb126c25caccdb
+size 5560

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}