Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-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 0.10.1.dev0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a4e760c305f96bfbfbaed075297e74158a25dfe85f204dd87ef8dad46d8966
+size 335604696

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b9ffec74c087950cb734f3928e0998c1f6510d6910a989eb3cc6cfc1c073a1
+size 168624724

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055122a7cf0e08fc49045543fb92078f60d7372480f6968160cb24b2494b6226
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913fc19bf2ad8265632a721056db64133a2c28d72c90664e19bbea762ef652b8
+size 1064

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 3,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 25.49334716796875,
+      "learning_rate": 2e-05,
+      "loss": 6.6468,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 7.297876834869385,
+      "eval_runtime": 19.9721,
+      "eval_samples_per_second": 0.601,
+      "eval_steps_per_second": 0.3,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 25.83477020263672,
+      "learning_rate": 4e-05,
+      "loss": 7.0344,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 29.465993881225586,
+      "learning_rate": 6e-05,
+      "loss": 7.0949,
+      "step": 3
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 5.278209209442139,
+      "eval_runtime": 20.1162,
+      "eval_samples_per_second": 0.597,
+      "eval_steps_per_second": 0.298,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 22.357271194458008,
+      "learning_rate": 8e-05,
+      "loss": 5.4423,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.18695068359375,
+      "learning_rate": 0.0001,
+      "loss": 3.2963,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 11.463640213012695,
+      "learning_rate": 0.00012,
+      "loss": 1.3638,
+      "step": 6
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.8664708733558655,
+      "eval_runtime": 20.0662,
+      "eval_samples_per_second": 0.598,
+      "eval_steps_per_second": 0.299,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.263468265533447,
+      "learning_rate": 0.00014,
+      "loss": 0.6614,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.55341911315918,
+      "learning_rate": 0.00016,
+      "loss": 0.5933,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.804744720458984,
+      "learning_rate": 0.00018,
+      "loss": 0.53,
+      "step": 9
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.6486384868621826,
+      "eval_runtime": 19.9911,
+      "eval_samples_per_second": 0.6,
+      "eval_steps_per_second": 0.3,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 14.322916030883789,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.152796745300293,
+      "learning_rate": 0.0001,
+      "loss": 0.5521,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.4037420749664307,
+      "learning_rate": 0.0,
+      "loss": 0.4866,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.4921029508113861,
+      "eval_runtime": 19.9358,
+      "eval_samples_per_second": 0.602,
+      "eval_steps_per_second": 0.301,
+      "step": 12
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 12,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 3.394812802970419e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbf5ce5d56cf3842d5eeddef21bd03852f88b039372750690d17f74ff4c733c
+size 5624