Upload 51 files

README.md

@@ -0,0 +1,165 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: adapters/hw-infi-qlora-10-epoch-16384-contex
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: bshada/hw-infi
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./adapters/hw-infi-qlora-10-epoch-16384-contex
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 16384
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+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:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 10
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+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: 0
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# adapters/hw-infi-qlora-10-epoch-16384-contex
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2161
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2155        | 0.5   | 1    | 0.2359          |
+| 0.2104        | 1.0   | 2    | 0.2150          |
+| 0.1625        | 1.5   | 3    | 0.1978          |
+| 0.1496        | 2.0   | 4    | 0.1850          |
+| 0.1264        | 2.5   | 5    | 0.1786          |
+| 0.11          | 3.0   | 6    | 0.1812          |
+| 0.091         | 3.5   | 7    | 0.1830          |
+| 0.1007        | 4.0   | 8    | 0.1835          |
+| 0.0623        | 4.5   | 9    | 0.1880          |
+| 0.082         | 5.0   | 10   | 0.1919          |
+| 0.0405        | 5.5   | 11   | 0.1971          |
+| 0.0636        | 6.0   | 12   | 0.2002          |
+| 0.054         | 6.5   | 13   | 0.2056          |
+| 0.0293        | 7.0   | 14   | 0.2076          |
+| 0.0406        | 7.5   | 15   | 0.2110          |
+| 0.0192        | 8.0   | 16   | 0.2140          |
+| 0.034         | 8.5   | 17   | 0.2148          |
+| 0.0153        | 9.0   | 18   | 0.2158          |
+| 0.0314        | 9.5   | 19   | 0.2161          |
+| 0.0142        | 10.0  | 20   | 0.2161          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5643c1ee141dd1a74ec8cf576b71ed657a342e3d892039088c2b13cf60a453fe
+size 167934026

checkpoint-14/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-14/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-14/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b9da15af3aef973e31beabd789a7eb1a5339cc72155c6aee4233e1c634f35f
+size 167832688

checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a6c6cbdd43f702e73394ff96bde8eedd40946f01e3cd0232f202518d5d1226
+size 168624724

checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce68b8115b755c4a4e25cd1170099185d4e74db9c37e93bc6fd65df8e9a25e2a
+size 14244

checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45123163216752bf36cb4910bab13325f3d253fd6ebf678d91470edb6929de5e
+size 1064

checkpoint-14/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
+  }
+}

checkpoint-14/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-14/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 1,
+  "global_step": 14,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.201171875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.2155,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.23589570820331573,
+      "eval_runtime": 6.9655,
+      "eval_samples_per_second": 0.144,
+      "eval_steps_per_second": 0.144,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.2104,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2149593085050583,
+      "eval_runtime": 7.0061,
+      "eval_samples_per_second": 0.143,
+      "eval_steps_per_second": 0.143,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.1625,
+      "step": 3
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.19781844317913055,
+      "eval_runtime": 7.0431,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.1496,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18500646948814392,
+      "eval_runtime": 7.0667,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.1264,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.17856794595718384,
+      "eval_runtime": 7.1001,
+      "eval_samples_per_second": 0.141,
+      "eval_steps_per_second": 0.141,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.11,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1812315732240677,
+      "eval_runtime": 7.1196,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.091,
+      "step": 7
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.18298085033893585,
+      "eval_runtime": 7.1414,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1007,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1835242211818695,
+      "eval_runtime": 7.1478,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0623,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.18798375129699707,
+      "eval_runtime": 7.1753,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001,
+      "loss": 0.082,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19188430905342102,
+      "eval_runtime": 7.1823,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.1953125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0405,
+      "step": 11
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.19711872935295105,
+      "eval_runtime": 7.1989,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.16796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0636,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.20024314522743225,
+      "eval_runtime": 7.1756,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.15234375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.054,
+      "step": 13
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.20560228824615479,
+      "eval_runtime": 7.1855,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.37109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0293,
+      "step": 14
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2076297104358673,
+      "eval_runtime": 7.1951,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 14
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9905866669031424.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07adafd16ce083b1e334fbdc9f6d619e148eda3db7571a3ce3f9391877f01363
+size 6072

checkpoint-16/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-16/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-16/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eed375b7bc989d56b83ad5c82033cc08dc8783d2b6b0ae7c28f2106db90646
+size 167832688

checkpoint-16/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d725169a6275b27872bdefa94aa41c4dd36c8c1da98395c2560bccc81b1f8cd
+size 168624724

checkpoint-16/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3341ddb6e8ff15189725c97f6449e39b27fdc5608f4fa6076d0e5ebd83a253af
+size 14244

checkpoint-16/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c84577e6c9d054a8b86ed72f08846c62432c6eca96a5b8a15f514e5ea73b326
+size 1064

checkpoint-16/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
+  }
+}

checkpoint-16/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-16/trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 1,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.201171875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.2155,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.23589570820331573,
+      "eval_runtime": 6.9655,
+      "eval_samples_per_second": 0.144,
+      "eval_steps_per_second": 0.144,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.2104,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2149593085050583,
+      "eval_runtime": 7.0061,
+      "eval_samples_per_second": 0.143,
+      "eval_steps_per_second": 0.143,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.1625,
+      "step": 3
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.19781844317913055,
+      "eval_runtime": 7.0431,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.1496,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18500646948814392,
+      "eval_runtime": 7.0667,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.1264,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.17856794595718384,
+      "eval_runtime": 7.1001,
+      "eval_samples_per_second": 0.141,
+      "eval_steps_per_second": 0.141,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.11,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1812315732240677,
+      "eval_runtime": 7.1196,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.091,
+      "step": 7
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.18298085033893585,
+      "eval_runtime": 7.1414,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1007,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1835242211818695,
+      "eval_runtime": 7.1478,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0623,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.18798375129699707,
+      "eval_runtime": 7.1753,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001,
+      "loss": 0.082,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19188430905342102,
+      "eval_runtime": 7.1823,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.1953125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0405,
+      "step": 11
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.19711872935295105,
+      "eval_runtime": 7.1989,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.16796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0636,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.20024314522743225,
+      "eval_runtime": 7.1756,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.15234375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.054,
+      "step": 13
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.20560228824615479,
+      "eval_runtime": 7.1855,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.37109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0293,
+      "step": 14
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2076297104358673,
+      "eval_runtime": 7.1951,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 14
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.162109375,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0406,
+      "step": 15
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.21104469895362854,
+      "eval_runtime": 7.1938,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 15
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.150390625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0192,
+      "step": 16
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.21401870250701904,
+      "eval_runtime": 7.2017,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 16
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1320990478893056e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07adafd16ce083b1e334fbdc9f6d619e148eda3db7571a3ce3f9391877f01363
+size 6072

checkpoint-18/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-18/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ad77935285bf8c021bc377fe1b0055e2888afad2f6d69385dc592bd117d745
+size 167832688

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0433f3be294f9c7ea12e69a2d32d57be793c23fe6350474270aea22632fa7eaf
+size 168624724

checkpoint-18/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8275ada323dfe0e439a4e6b300f8cf49e0e990497886568a45eccb5174d2d90a
+size 14244

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1953390b5e2705c59a40cf26401a7f8fd783ef85c361a958d772e02cd4ec2d
+size 1064

checkpoint-18/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
+  }
+}

checkpoint-18/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-18/trainer_state.json

@@ -0,0 +1,303 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 1,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.201171875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.2155,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.23589570820331573,
+      "eval_runtime": 6.9655,
+      "eval_samples_per_second": 0.144,
+      "eval_steps_per_second": 0.144,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.2104,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2149593085050583,
+      "eval_runtime": 7.0061,
+      "eval_samples_per_second": 0.143,
+      "eval_steps_per_second": 0.143,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.1625,
+      "step": 3
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.19781844317913055,
+      "eval_runtime": 7.0431,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.1496,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18500646948814392,
+      "eval_runtime": 7.0667,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.1264,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.17856794595718384,
+      "eval_runtime": 7.1001,
+      "eval_samples_per_second": 0.141,
+      "eval_steps_per_second": 0.141,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.11,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1812315732240677,
+      "eval_runtime": 7.1196,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.091,
+      "step": 7
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.18298085033893585,
+      "eval_runtime": 7.1414,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1007,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1835242211818695,
+      "eval_runtime": 7.1478,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0623,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.18798375129699707,
+      "eval_runtime": 7.1753,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001,
+      "loss": 0.082,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19188430905342102,
+      "eval_runtime": 7.1823,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.1953125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0405,
+      "step": 11
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.19711872935295105,
+      "eval_runtime": 7.1989,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.16796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0636,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.20024314522743225,
+      "eval_runtime": 7.1756,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.15234375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.054,
+      "step": 13
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.20560228824615479,
+      "eval_runtime": 7.1855,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.37109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0293,
+      "step": 14
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2076297104358673,
+      "eval_runtime": 7.1951,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 14
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.162109375,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0406,
+      "step": 15
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.21104469895362854,
+      "eval_runtime": 7.1938,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 15
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.150390625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0192,
+      "step": 16
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.21401870250701904,
+      "eval_runtime": 7.2017,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 16
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.140625,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.034,
+      "step": 17
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 0.21480436623096466,
+      "eval_runtime": 7.1945,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 17
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0153,
+      "step": 18
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.21578560769557953,
+      "eval_runtime": 7.2039,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 18
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2736114288754688e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07adafd16ce083b1e334fbdc9f6d619e148eda3db7571a3ce3f9391877f01363
+size 6072

checkpoint-20/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-20/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-20/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f801a8e14488b2fb8330fcca470bc444c6c0b8554be764394388106feab96766
+size 167832688

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0539b9ccf15443d6ed401a5139ae03bddde1da6fdc3af1eac1412784994d55c
+size 168624724

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acc796244e531cf6c179b3cd43ac20dda81cd14e0835699a2aed5c06282aa2f
+size 14244

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
+size 1064

checkpoint-20/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
+  }
+}

checkpoint-20/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-20/trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 1,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.201171875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.2155,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.23589570820331573,
+      "eval_runtime": 6.9655,
+      "eval_samples_per_second": 0.144,
+      "eval_steps_per_second": 0.144,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.2104,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2149593085050583,
+      "eval_runtime": 7.0061,
+      "eval_samples_per_second": 0.143,
+      "eval_steps_per_second": 0.143,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.1625,
+      "step": 3
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.19781844317913055,
+      "eval_runtime": 7.0431,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.1496,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18500646948814392,
+      "eval_runtime": 7.0667,
+      "eval_samples_per_second": 0.142,
+      "eval_steps_per_second": 0.142,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.1264,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.17856794595718384,
+      "eval_runtime": 7.1001,
+      "eval_samples_per_second": 0.141,
+      "eval_steps_per_second": 0.141,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.11,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1812315732240677,
+      "eval_runtime": 7.1196,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.091,
+      "step": 7
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.18298085033893585,
+      "eval_runtime": 7.1414,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1007,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1835242211818695,
+      "eval_runtime": 7.1478,
+      "eval_samples_per_second": 0.14,
+      "eval_steps_per_second": 0.14,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0623,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.18798375129699707,
+      "eval_runtime": 7.1753,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001,
+      "loss": 0.082,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19188430905342102,
+      "eval_runtime": 7.1823,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.1953125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0405,
+      "step": 11
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.19711872935295105,
+      "eval_runtime": 7.1989,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.16796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0636,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.20024314522743225,
+      "eval_runtime": 7.1756,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.15234375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.054,
+      "step": 13
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.20560228824615479,
+      "eval_runtime": 7.1855,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.37109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0293,
+      "step": 14
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2076297104358673,
+      "eval_runtime": 7.1951,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 14
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.162109375,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0406,
+      "step": 15
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.21104469895362854,
+      "eval_runtime": 7.1938,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 15
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.150390625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0192,
+      "step": 16
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.21401870250701904,
+      "eval_runtime": 7.2017,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 16
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.140625,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.034,
+      "step": 17
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 0.21480436623096466,
+      "eval_runtime": 7.1945,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 17
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0153,
+      "step": 18
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.21578560769557953,
+      "eval_runtime": 7.2039,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 18
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0314,
+      "step": 19
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.2161264419555664,
+      "eval_runtime": 7.2003,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 19
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 0.0,
+      "loss": 0.0142,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.21610291302204132,
+      "eval_runtime": 7.2089,
+      "eval_samples_per_second": 0.139,
+      "eval_steps_per_second": 0.139,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.415123809861632e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07adafd16ce083b1e334fbdc9f6d619e148eda3db7571a3ce3f9391877f01363
+size 6072

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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_storage": "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": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 32768
+}

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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404