Upload 8 files

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.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "lm_head",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94e55d62a2be12e86ac9fec910f69a3b3c584c344583f5c9e6ff8180042d20e
+size 609389712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9956de091997ade300b414e60796b0834186e53c408c33e18b4e943723ccb9
+size 43126684

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfa6594e632142e730f2b0b2eb542928cf23ce59ae6fe7db395dc18f0e2aded
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a0a7460dd8b31647fa0542d6e8cdd02c31293f0704d27ec57a49b4c476aa1c
+size 1064

trainer_state.json

@@ -0,0 +1,495 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.044464206313917294,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 2.3656,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 2.2802,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4974874371859298e-05,
+      "loss": 2.2725,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.492462311557789e-05,
+      "loss": 2.0394,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4874371859296484e-05,
+      "loss": 2.1627,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4824120603015078e-05,
+      "loss": 2.093,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.477386934673367e-05,
+      "loss": 1.9071,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.4723618090452264e-05,
+      "loss": 1.854,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4673366834170854e-05,
+      "loss": 1.9392,
+      "step": 18
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.462311557788945e-05,
+      "loss": 1.9703,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.457286432160804e-05,
+      "loss": 1.8765,
+      "step": 22
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4522613065326637e-05,
+      "loss": 1.8566,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4472361809045227e-05,
+      "loss": 1.716,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.442211055276382e-05,
+      "loss": 1.7856,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4371859296482413e-05,
+      "loss": 1.7823,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4321608040201007e-05,
+      "loss": 1.7174,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.42713567839196e-05,
+      "loss": 1.6417,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.422110552763819e-05,
+      "loss": 1.6285,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4170854271356786e-05,
+      "loss": 1.8137,
+      "step": 38
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4120603015075376e-05,
+      "loss": 1.7487,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4070351758793973e-05,
+      "loss": 1.7974,
+      "step": 42
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4020100502512563e-05,
+      "loss": 1.7068,
+      "step": 44
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3969849246231156e-05,
+      "loss": 1.7251,
+      "step": 46
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.391959798994975e-05,
+      "loss": 1.7919,
+      "step": 48
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3869346733668342e-05,
+      "loss": 1.7122,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.7093677520751953,
+      "eval_runtime": 2707.7474,
+      "eval_samples_per_second": 5.695,
+      "eval_steps_per_second": 0.356,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3819095477386936e-05,
+      "loss": 1.6579,
+      "step": 52
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.376884422110553e-05,
+      "loss": 1.6581,
+      "step": 54
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3718592964824122e-05,
+      "loss": 1.7084,
+      "step": 56
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3668341708542715e-05,
+      "loss": 1.8677,
+      "step": 58
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.361809045226131e-05,
+      "loss": 1.6996,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3567839195979902e-05,
+      "loss": 1.6643,
+      "step": 62
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.351758793969849e-05,
+      "loss": 1.7271,
+      "step": 64
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3467336683417088e-05,
+      "loss": 1.722,
+      "step": 66
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3417085427135678e-05,
+      "loss": 1.5764,
+      "step": 68
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3366834170854275e-05,
+      "loss": 1.5796,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3316582914572865e-05,
+      "loss": 1.6595,
+      "step": 72
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.326633165829146e-05,
+      "loss": 1.7247,
+      "step": 74
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.321608040201005e-05,
+      "loss": 1.7143,
+      "step": 76
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3165829145728644e-05,
+      "loss": 1.7236,
+      "step": 78
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3115577889447238e-05,
+      "loss": 1.6257,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3065326633165827e-05,
+      "loss": 1.722,
+      "step": 82
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3015075376884424e-05,
+      "loss": 1.7404,
+      "step": 84
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2964824120603014e-05,
+      "loss": 1.7458,
+      "step": 86
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.291457286432161e-05,
+      "loss": 1.5463,
+      "step": 88
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.28643216080402e-05,
+      "loss": 1.6731,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2814070351758797e-05,
+      "loss": 1.5564,
+      "step": 92
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2763819095477387e-05,
+      "loss": 1.8338,
+      "step": 94
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.271356783919598e-05,
+      "loss": 1.6688,
+      "step": 96
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2663316582914573e-05,
+      "loss": 1.6844,
+      "step": 98
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2613065326633167e-05,
+      "loss": 1.6507,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.6832690238952637,
+      "eval_runtime": 2705.0606,
+      "eval_samples_per_second": 5.701,
+      "eval_steps_per_second": 0.356,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.256281407035176e-05,
+      "loss": 1.6102,
+      "step": 102
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2512562814070353e-05,
+      "loss": 1.8097,
+      "step": 104
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2462311557788946e-05,
+      "loss": 1.6539,
+      "step": 106
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.241206030150754e-05,
+      "loss": 1.6334,
+      "step": 108
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2361809045226133e-05,
+      "loss": 1.704,
+      "step": 110
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2311557788944726e-05,
+      "loss": 1.6663,
+      "step": 112
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2261306532663316e-05,
+      "loss": 1.6988,
+      "step": 114
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2211055276381913e-05,
+      "loss": 1.5737,
+      "step": 116
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.2160804020100502e-05,
+      "loss": 1.6554,
+      "step": 118
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.21105527638191e-05,
+      "loss": 1.6942,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.206030150753769e-05,
+      "loss": 1.5815,
+      "step": 122
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.2010050251256282e-05,
+      "loss": 1.577,
+      "step": 124
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1959798994974875e-05,
+      "loss": 1.7271,
+      "step": 126
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.190954773869347e-05,
+      "loss": 1.6922,
+      "step": 128
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1859296482412062e-05,
+      "loss": 1.5486,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1809045226130652e-05,
+      "loss": 1.7836,
+      "step": 132
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.175879396984925e-05,
+      "loss": 1.5733,
+      "step": 134
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1708542713567838e-05,
+      "loss": 1.5774,
+      "step": 136
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1658291457286435e-05,
+      "loss": 1.6749,
+      "step": 138
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1608040201005025e-05,
+      "loss": 1.6127,
+      "step": 140
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.155778894472362e-05,
+      "loss": 1.7014,
+      "step": 142
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.150753768844221e-05,
+      "loss": 1.5019,
+      "step": 144
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1457286432160804e-05,
+      "loss": 1.6754,
+      "step": 146
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.1407035175879398e-05,
+      "loss": 1.607,
+      "step": 148
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.135678391959799e-05,
+      "loss": 1.6015,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 1.6669741868972778,
+      "eval_runtime": 2712.7443,
+      "eval_samples_per_second": 5.685,
+      "eval_steps_per_second": 0.355,
+      "step": 150
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 1.540494802944e+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:fdd2ab7aa962ee00be6d62f949a2231bcbdc87b87e4e4dc419777ebaad9c12d8
+size 4728