Upload 12 files

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c56e90c5881d9c9ee4a39ca33993dc12117d1050247e21dcb7eeb61bcf46c5f
+size 109071352

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8dab4a7d1f066a613ded093c88c6a1a6af7a91a0854a0aa4e6c92a2733bd89
+size 218211962

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c0261072c08c1c39369abadd29d0b19fd78e4ece7f0bb1a9951cadb17a9dd5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc4029c6b0e73ce66df9d2f36a2a8474285f2c376eb0b0d608bfed2941943a6
+size 1064

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 +1,42 @@
+{
+  "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>",
+  "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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,341 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.571428571428571,
+  "eval_steps": 20,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.269596129655838,
+      "eval_runtime": 41.7008,
+      "eval_samples_per_second": 3.285,
+      "eval_steps_per_second": 0.432,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3253,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.2160598337650299,
+      "eval_runtime": 41.6766,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.432,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.5e-05,
+      "loss": 0.25,
+      "step": 50
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.2049967646598816,
+      "eval_runtime": 41.643,
+      "eval_samples_per_second": 3.29,
+      "eval_steps_per_second": 0.432,
+      "step": 60
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2212,
+      "step": 75
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.20088960230350494,
+      "eval_runtime": 41.6399,
+      "eval_samples_per_second": 3.29,
+      "eval_steps_per_second": 0.432,
+      "step": 80
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2168,
+      "step": 100
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.19830842316150665,
+      "eval_runtime": 41.6606,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 0.432,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.1965203881263733,
+      "eval_runtime": 41.6343,
+      "eval_samples_per_second": 3.291,
+      "eval_steps_per_second": 0.432,
+      "step": 120
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.5e-05,
+      "loss": 0.211,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.19506876170635223,
+      "eval_runtime": 41.6134,
+      "eval_samples_per_second": 3.292,
+      "eval_steps_per_second": 0.433,
+      "step": 140
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2198,
+      "step": 150
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.19399328529834747,
+      "eval_runtime": 41.7184,
+      "eval_samples_per_second": 3.284,
+      "eval_steps_per_second": 0.431,
+      "step": 160
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2018,
+      "step": 175
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.19290637969970703,
+      "eval_runtime": 41.6764,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.432,
+      "step": 180
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2161,
+      "step": 200
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.19207116961479187,
+      "eval_runtime": 41.9073,
+      "eval_samples_per_second": 3.269,
+      "eval_steps_per_second": 0.43,
+      "step": 200
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.19164356589317322,
+      "eval_runtime": 41.7357,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 0.431,
+      "step": 220
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1967,
+      "step": 225
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.19071181118488312,
+      "eval_runtime": 41.6774,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.432,
+      "step": 240
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2225,
+      "step": 250
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.1900840550661087,
+      "eval_runtime": 41.6631,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 0.432,
+      "step": 260
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2038,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18933609127998352,
+      "eval_runtime": 41.6745,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.432,
+      "step": 280
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2065,
+      "step": 300
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.18885642290115356,
+      "eval_runtime": 41.7299,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 0.431,
+      "step": 300
+    },
+    {
+      "epoch": 2.29,
+      "eval_loss": 0.18856477737426758,
+      "eval_runtime": 41.7641,
+      "eval_samples_per_second": 3.28,
+      "eval_steps_per_second": 0.431,
+      "step": 320
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1962,
+      "step": 325
+    },
+    {
+      "epoch": 2.43,
+      "eval_loss": 0.1882474571466446,
+      "eval_runtime": 41.7165,
+      "eval_samples_per_second": 3.284,
+      "eval_steps_per_second": 0.431,
+      "step": 340
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2058,
+      "step": 350
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.1876191794872284,
+      "eval_runtime": 41.6862,
+      "eval_samples_per_second": 3.286,
+      "eval_steps_per_second": 0.432,
+      "step": 360
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1935,
+      "step": 375
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 0.18731944262981415,
+      "eval_runtime": 41.649,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 0.432,
+      "step": 380
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2191,
+      "step": 400
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.18684075772762299,
+      "eval_runtime": 41.636,
+      "eval_samples_per_second": 3.29,
+      "eval_steps_per_second": 0.432,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.18620511889457703,
+      "eval_runtime": 41.6932,
+      "eval_samples_per_second": 3.286,
+      "eval_steps_per_second": 0.432,
+      "step": 420
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1848,
+      "step": 425
+    },
+    {
+      "epoch": 3.14,
+      "eval_loss": 0.1859755963087082,
+      "eval_runtime": 41.7348,
+      "eval_samples_per_second": 3.283,
+      "eval_steps_per_second": 0.431,
+      "step": 440
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1797,
+      "step": 450
+    },
+    {
+      "epoch": 3.29,
+      "eval_loss": 0.1856825351715088,
+      "eval_runtime": 41.6956,
+      "eval_samples_per_second": 3.286,
+      "eval_steps_per_second": 0.432,
+      "step": 460
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2054,
+      "step": 475
+    },
+    {
+      "epoch": 3.43,
+      "eval_loss": 0.18539157509803772,
+      "eval_runtime": 41.683,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.432,
+      "step": 480
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 2.5e-05,
+      "loss": 0.206,
+      "step": 500
+    },
+    {
+      "epoch": 3.57,
+      "eval_loss": 0.18517018854618073,
+      "eval_runtime": 41.665,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 0.432,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 25,
+  "total_flos": 1.7463220022909338e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385b11df4a92033b1e85d26e4c223af491f6a7a3959dd2f6a21e3083efb4580d
+size 4728