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 0.11.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "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,
+  "layer_replication": null,
+  "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": [
+    "lm_head",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_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:b1b023e63d3d49663187565c66d202c779dadf2af865d332643bd4a963125534
+size 864513616

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09e27bfe92af082f26ca35e2a8a430e28f19e07d4e7ebdf61a9020abfea0730
+size 170951516

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7244f6a688587faec5933a619aedf9bee24bdb758f09e232ec12eafba59f153
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1a60295248dfe1aa7406d87611d52c66f3d8cd2a7f9d012a920e5f749dc67b
+size 1064

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0025,
+      "grad_norm": 3.0887749195098877,
+      "learning_rate": 2.384538152610442e-06,
+      "loss": 0.7185,
+      "step": 25
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 3.3972108364105225,
+      "learning_rate": 2.2590361445783136e-06,
+      "loss": 0.7207,
+      "step": 50
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 2.799666166305542,
+      "learning_rate": 2.1335341365461848e-06,
+      "loss": 0.6349,
+      "step": 75
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.892286539077759,
+      "learning_rate": 2.0080321285140564e-06,
+      "loss": 0.609,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.9785426259040833,
+      "eval_runtime": 50.0276,
+      "eval_samples_per_second": 0.999,
+      "eval_steps_per_second": 0.14,
+      "step": 100
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 2.4466898441314697,
+      "learning_rate": 1.882530120481928e-06,
+      "loss": 0.6208,
+      "step": 125
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 2.5951688289642334,
+      "learning_rate": 1.7570281124497993e-06,
+      "loss": 0.6043,
+      "step": 150
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 2.5070278644561768,
+      "learning_rate": 1.6315261044176709e-06,
+      "loss": 0.6723,
+      "step": 175
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.5609757900238037,
+      "learning_rate": 1.5060240963855425e-06,
+      "loss": 0.5984,
+      "step": 200
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 0.985219419002533,
+      "eval_runtime": 49.8634,
+      "eval_samples_per_second": 1.003,
+      "eval_steps_per_second": 0.14,
+      "step": 200
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 3.5456857681274414,
+      "learning_rate": 1.3805220883534137e-06,
+      "loss": 0.5879,
+      "step": 225
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 3.7330322265625,
+      "learning_rate": 1.2550200803212854e-06,
+      "loss": 0.604,
+      "step": 250
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 2.9475417137145996,
+      "learning_rate": 1.1295180722891568e-06,
+      "loss": 0.545,
+      "step": 275
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.689638137817383,
+      "learning_rate": 1.0040160642570282e-06,
+      "loss": 0.5419,
+      "step": 300
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9883354306221008,
+      "eval_runtime": 49.9109,
+      "eval_samples_per_second": 1.002,
+      "eval_steps_per_second": 0.14,
+      "step": 300
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 4.0419721603393555,
+      "learning_rate": 8.785140562248996e-07,
+      "loss": 0.52,
+      "step": 325
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.243961811065674,
+      "learning_rate": 7.530120481927713e-07,
+      "loss": 0.6001,
+      "step": 350
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 3.7675397396087646,
+      "learning_rate": 6.275100401606427e-07,
+      "loss": 0.5309,
+      "step": 375
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.4450817108154297,
+      "learning_rate": 5.020080321285141e-07,
+      "loss": 0.5738,
+      "step": 400
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.9952414035797119,
+      "eval_runtime": 50.0075,
+      "eval_samples_per_second": 1.0,
+      "eval_steps_per_second": 0.14,
+      "step": 400
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 3.5277650356292725,
+      "learning_rate": 3.7650602409638563e-07,
+      "loss": 0.6085,
+      "step": 425
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 4.167781829833984,
+      "learning_rate": 2.5100401606425705e-07,
+      "loss": 0.6188,
+      "step": 450
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 3.9890384674072266,
+      "learning_rate": 1.2550200803212853e-07,
+      "loss": 0.5281,
+      "step": 475
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.777990341186523,
+      "learning_rate": 0.0,
+      "loss": 0.6808,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.9945573210716248,
+      "eval_runtime": 50.1662,
+      "eval_samples_per_second": 0.997,
+      "eval_steps_per_second": 0.14,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1052597116928e+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 sha256:4c023baf47d2188eaa87ff0d8225b466213cc354f5ea3fd0370a58f6d69a4f39
+size 5048