Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-128k-instruct
+---
+
+# 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 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
+  "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": [
+    "qkv_proj",
+    "gate_up_proj",
+    "down_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 sha256:743e48774655a4e140dfe3ff859b1e9d51f4819517364a0ee8adce5db60b9237
+size 176186776

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becd5b410b04b37d53e42908de6589a6cc9f6aee843474d0915dde3b093cb8f4
+size 88481082

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc2e12700853d478a84a453e800b0ddc018d3b5bb423231eb5389f21b3fc888
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4ab5f608c113ef9b81b5921bd661a21962184c52075538ed871611015781ce
+size 1064

trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09615384615384616,
+  "eval_steps": 25,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004807692307692308,
+      "grad_norm": 8.379351615905762,
+      "learning_rate": 2.3797595190380762e-05,
+      "loss": 2.1609,
+      "step": 25
+    },
+    {
+      "epoch": 0.004807692307692308,
+      "eval_loss": 2.1636602878570557,
+      "eval_runtime": 291.2358,
+      "eval_samples_per_second": 8.931,
+      "eval_steps_per_second": 1.119,
+      "step": 25
+    },
+    {
+      "epoch": 0.009615384615384616,
+      "grad_norm": 2.0016415119171143,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 2.1269,
+      "step": 50
+    },
+    {
+      "epoch": 0.009615384615384616,
+      "eval_loss": 2.119358777999878,
+      "eval_runtime": 289.2623,
+      "eval_samples_per_second": 8.992,
+      "eval_steps_per_second": 1.127,
+      "step": 50
+    },
+    {
+      "epoch": 0.014423076923076924,
+      "grad_norm": 2.0613415241241455,
+      "learning_rate": 2.1292585170340683e-05,
+      "loss": 2.0789,
+      "step": 75
+    },
+    {
+      "epoch": 0.014423076923076924,
+      "eval_loss": 2.1015028953552246,
+      "eval_runtime": 289.6241,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 1.126,
+      "step": 75
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 1.8239314556121826,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 2.1804,
+      "step": 100
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "eval_loss": 2.0893497467041016,
+      "eval_runtime": 289.6046,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 1.126,
+      "step": 100
+    },
+    {
+      "epoch": 0.02403846153846154,
+      "grad_norm": 2.4804182052612305,
+      "learning_rate": 1.87875751503006e-05,
+      "loss": 2.0228,
+      "step": 125
+    },
+    {
+      "epoch": 0.02403846153846154,
+      "eval_loss": 2.078104019165039,
+      "eval_runtime": 289.573,
+      "eval_samples_per_second": 8.982,
+      "eval_steps_per_second": 1.126,
+      "step": 125
+    },
+    {
+      "epoch": 0.028846153846153848,
+      "grad_norm": 1.7520055770874023,
+      "learning_rate": 1.7535070140280564e-05,
+      "loss": 2.0352,
+      "step": 150
+    },
+    {
+      "epoch": 0.028846153846153848,
+      "eval_loss": 2.070697784423828,
+      "eval_runtime": 289.6185,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 1.126,
+      "step": 150
+    },
+    {
+      "epoch": 0.03365384615384615,
+      "grad_norm": 2.02740216255188,
+      "learning_rate": 1.628256513026052e-05,
+      "loss": 2.1509,
+      "step": 175
+    },
+    {
+      "epoch": 0.03365384615384615,
+      "eval_loss": 2.062859535217285,
+      "eval_runtime": 289.6496,
+      "eval_samples_per_second": 8.98,
+      "eval_steps_per_second": 1.125,
+      "step": 175
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 2.1709401607513428,
+      "learning_rate": 1.5030060120240483e-05,
+      "loss": 2.0341,
+      "step": 200
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "eval_loss": 2.053925037384033,
+      "eval_runtime": 289.7733,
+      "eval_samples_per_second": 8.976,
+      "eval_steps_per_second": 1.125,
+      "step": 200
+    },
+    {
+      "epoch": 0.04326923076923077,
+      "grad_norm": 2.202911853790283,
+      "learning_rate": 1.3777555110220442e-05,
+      "loss": 2.0211,
+      "step": 225
+    },
+    {
+      "epoch": 0.04326923076923077,
+      "eval_loss": 2.049743413925171,
+      "eval_runtime": 289.6071,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 1.126,
+      "step": 225
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 2.2768239974975586,
+      "learning_rate": 1.25250501002004e-05,
+      "loss": 2.0178,
+      "step": 250
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "eval_loss": 2.041290521621704,
+      "eval_runtime": 289.3413,
+      "eval_samples_per_second": 8.989,
+      "eval_steps_per_second": 1.127,
+      "step": 250
+    },
+    {
+      "epoch": 0.052884615384615384,
+      "grad_norm": 2.3528246879577637,
+      "learning_rate": 1.1272545090180361e-05,
+      "loss": 1.9976,
+      "step": 275
+    },
+    {
+      "epoch": 0.052884615384615384,
+      "eval_loss": 2.0366218090057373,
+      "eval_runtime": 289.4271,
+      "eval_samples_per_second": 8.987,
+      "eval_steps_per_second": 1.126,
+      "step": 275
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "grad_norm": 2.196848154067993,
+      "learning_rate": 1.0020040080160322e-05,
+      "loss": 2.0639,
+      "step": 300
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "eval_loss": 2.0322206020355225,
+      "eval_runtime": 290.5527,
+      "eval_samples_per_second": 8.952,
+      "eval_steps_per_second": 1.122,
+      "step": 300
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 2.3414223194122314,
+      "learning_rate": 8.767535070140282e-06,
+      "loss": 2.0228,
+      "step": 325
+    },
+    {
+      "epoch": 0.0625,
+      "eval_loss": 2.0314226150512695,
+      "eval_runtime": 289.2882,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 1.127,
+      "step": 325
+    },
+    {
+      "epoch": 0.0673076923076923,
+      "grad_norm": 2.1816813945770264,
+      "learning_rate": 7.515030060120242e-06,
+      "loss": 1.9671,
+      "step": 350
+    },
+    {
+      "epoch": 0.0673076923076923,
+      "eval_loss": 2.0291802883148193,
+      "eval_runtime": 289.5519,
+      "eval_samples_per_second": 8.983,
+      "eval_steps_per_second": 1.126,
+      "step": 350
+    },
+    {
+      "epoch": 0.07211538461538461,
+      "grad_norm": 3.665743350982666,
+      "learning_rate": 6.2625250501002e-06,
+      "loss": 2.0339,
+      "step": 375
+    },
+    {
+      "epoch": 0.07211538461538461,
+      "eval_loss": 2.0244317054748535,
+      "eval_runtime": 289.4405,
+      "eval_samples_per_second": 8.986,
+      "eval_steps_per_second": 1.126,
+      "step": 375
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 3.862074136734009,
+      "learning_rate": 5.010020040080161e-06,
+      "loss": 1.9846,
+      "step": 400
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "eval_loss": 2.0220189094543457,
+      "eval_runtime": 289.1563,
+      "eval_samples_per_second": 8.995,
+      "eval_steps_per_second": 1.127,
+      "step": 400
+    },
+    {
+      "epoch": 0.08173076923076923,
+      "grad_norm": 2.982481002807617,
+      "learning_rate": 3.757515030060121e-06,
+      "loss": 1.9906,
+      "step": 425
+    },
+    {
+      "epoch": 0.08173076923076923,
+      "eval_loss": 2.0202925205230713,
+      "eval_runtime": 290.9218,
+      "eval_samples_per_second": 8.941,
+      "eval_steps_per_second": 1.121,
+      "step": 425
+    },
+    {
+      "epoch": 0.08653846153846154,
+      "grad_norm": 2.838700771331787,
+      "learning_rate": 2.5050100200400804e-06,
+      "loss": 2.0121,
+      "step": 450
+    },
+    {
+      "epoch": 0.08653846153846154,
+      "eval_loss": 2.018867254257202,
+      "eval_runtime": 290.201,
+      "eval_samples_per_second": 8.963,
+      "eval_steps_per_second": 1.123,
+      "step": 450
+    },
+    {
+      "epoch": 0.09134615384615384,
+      "grad_norm": 3.2099339962005615,
+      "learning_rate": 1.2525050100200402e-06,
+      "loss": 2.0468,
+      "step": 475
+    },
+    {
+      "epoch": 0.09134615384615384,
+      "eval_loss": 2.017698287963867,
+      "eval_runtime": 289.3362,
+      "eval_samples_per_second": 8.99,
+      "eval_steps_per_second": 1.127,
+      "step": 475
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 3.2114524841308594,
+      "learning_rate": 0.0,
+      "loss": 1.9998,
+      "step": 500
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "eval_loss": 2.01784086227417,
+      "eval_runtime": 287.7313,
+      "eval_samples_per_second": 9.04,
+      "eval_steps_per_second": 1.133,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4519942963200000.0,
+  "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:e53f57a9f5765c4777a1dace26377cd2c91e9bf38f8f86b05b7f25261172c7c8
+size 5048