Upload 8 files

README.md

@@ -1,3 +1,204 @@
 ---
-license: cc-by-nc-4.0
+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 0.7.2.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 64,
+  "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": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74ac426c07ba6c22cf6b6cb176e6343a291e2701139c8422dcf80c902a907be
+size 864513616

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ceca579432736fd411b7ab373adf53b0c27375ebdd47dec5e55af6a3826b07
+size 170951516

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b513875913060538872c064895d431153432656af6aaa1d66f1e1b676411d3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9789194b666d4c15bc7445f1d6efa16ed4dcc651200f8c8793eccae2c71ede2
+size 1064

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.230769230769231,
+  "eval_steps": 220,
+  "global_step": 440,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018906605922551254,
+      "loss": 1.1294,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00017767653758542142,
+      "loss": 1.0356,
+      "step": 50
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001662870159453303,
+      "loss": 1.0107,
+      "step": 75
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001548974943052392,
+      "loss": 1.1191,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00014350797266514807,
+      "loss": 0.7423,
+      "step": 125
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00013211845102505695,
+      "loss": 0.6658,
+      "step": 150
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00012072892938496582,
+      "loss": 0.5811,
+      "step": 175
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00010933940774487472,
+      "loss": 0.5556,
+      "step": 200
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 0.3080795109272003,
+      "eval_runtime": 199.9175,
+      "eval_samples_per_second": 1.035,
+      "eval_steps_per_second": 0.13,
+      "step": 220
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.79498861047836e-05,
+      "loss": 0.3572,
+      "step": 225
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.656036446469249e-05,
+      "loss": 0.2907,
+      "step": 250
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.517084282460137e-05,
+      "loss": 0.3575,
+      "step": 275
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 6.378132118451025e-05,
+      "loss": 0.3076,
+      "step": 300
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.239179954441914e-05,
+      "loss": 0.2052,
+      "step": 325
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 4.100227790432802e-05,
+      "loss": 0.137,
+      "step": 350
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 2.96127562642369e-05,
+      "loss": 0.1223,
+      "step": 375
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.8223234624145787e-05,
+      "loss": 0.1175,
+      "step": 400
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 6.83371298405467e-06,
+      "loss": 0.1137,
+      "step": 425
+    },
+    {
+      "epoch": 4.23,
+      "eval_loss": 0.052269067615270615,
+      "eval_runtime": 199.3757,
+      "eval_samples_per_second": 1.038,
+      "eval_steps_per_second": 0.13,
+      "step": 440
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 220,
+  "total_flos": 1.5491320119086285e+17,
+  "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 sha256:4a5cf6a0ee5f5ece657f3ccae130c44caa4a11d8c1eeb328ce21d4af559d79d8
+size 4728