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 +1,31 @@
+{
+  "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": 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": [
+    "down_proj",
+    "qkv_proj",
+    "o_proj",
+    "gate_up_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 sha256:7f0fc23f20ea4e7e160f32a344edcac6eba6ce480b96df17689e13e6d50e2ee2
+size 50365768

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd58bcb3641436686a49649be5d2ec449ec2b668c8ba2412b4e5643c0cc24b72
+size 25498516

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e6f6cd966b7b3a258817981a64c550d2326dba59fb81bdaed73b42ba83cc9c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406a86fe5ef81a1f6ff633f34d8a8e9dfbecdda2bd4f8a43f63eafb80e4d47e8
+size 1064

trainer_state.json

@@ -0,0 +1,481 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9992985737666586,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04676174888940846,
+      "grad_norm": 0.414691299200058,
+      "learning_rate": 9.923004399748587e-06,
+      "loss": 1.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.09352349777881692,
+      "grad_norm": 0.373704195022583,
+      "learning_rate": 9.765870521684476e-06,
+      "loss": 1.2045,
+      "step": 200
+    },
+    {
+      "epoch": 0.1402852466682254,
+      "grad_norm": 0.4187537431716919,
+      "learning_rate": 9.608736643620365e-06,
+      "loss": 1.2093,
+      "step": 300
+    },
+    {
+      "epoch": 0.18704699555763385,
+      "grad_norm": 0.49985188245773315,
+      "learning_rate": 9.451602765556255e-06,
+      "loss": 1.1465,
+      "step": 400
+    },
+    {
+      "epoch": 0.23380874444704233,
+      "grad_norm": 0.547389805316925,
+      "learning_rate": 9.294468887492145e-06,
+      "loss": 1.1502,
+      "step": 500
+    },
+    {
+      "epoch": 0.2805704933364508,
+      "grad_norm": 0.521124541759491,
+      "learning_rate": 9.137335009428033e-06,
+      "loss": 1.1455,
+      "step": 600
+    },
+    {
+      "epoch": 0.32733224222585927,
+      "grad_norm": 0.5321390628814697,
+      "learning_rate": 8.980201131363923e-06,
+      "loss": 1.1196,
+      "step": 700
+    },
+    {
+      "epoch": 0.3740939911152677,
+      "grad_norm": 0.5767441987991333,
+      "learning_rate": 8.823067253299812e-06,
+      "loss": 1.115,
+      "step": 800
+    },
+    {
+      "epoch": 0.4208557400046762,
+      "grad_norm": 0.6053145527839661,
+      "learning_rate": 8.6659333752357e-06,
+      "loss": 1.1419,
+      "step": 900
+    },
+    {
+      "epoch": 0.46761748889408467,
+      "grad_norm": 0.6067389249801636,
+      "learning_rate": 8.50879949717159e-06,
+      "loss": 1.1077,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5143792377834931,
+      "grad_norm": 0.6225459575653076,
+      "learning_rate": 8.35166561910748e-06,
+      "loss": 1.1181,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5611409866729016,
+      "grad_norm": 0.6895543932914734,
+      "learning_rate": 8.19453174104337e-06,
+      "loss": 1.1015,
+      "step": 1200
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 0.6458436846733093,
+      "learning_rate": 8.03739786297926e-06,
+      "loss": 1.1198,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6546644844517185,
+      "grad_norm": 0.663877010345459,
+      "learning_rate": 7.88026398491515e-06,
+      "loss": 1.0982,
+      "step": 1400
+    },
+    {
+      "epoch": 0.701426233341127,
+      "grad_norm": 0.6076435446739197,
+      "learning_rate": 7.723130106851037e-06,
+      "loss": 1.0911,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7481879822305354,
+      "grad_norm": 1.181686282157898,
+      "learning_rate": 7.565996228786927e-06,
+      "loss": 1.0917,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7949497311199439,
+      "grad_norm": 0.8685171008110046,
+      "learning_rate": 7.408862350722817e-06,
+      "loss": 1.0836,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8417114800093524,
+      "grad_norm": 0.7595590949058533,
+      "learning_rate": 7.251728472658706e-06,
+      "loss": 1.0937,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8884732288987608,
+      "grad_norm": 1.043165683746338,
+      "learning_rate": 7.0945945945945946e-06,
+      "loss": 1.0681,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9352349777881693,
+      "grad_norm": 0.7252351641654968,
+      "learning_rate": 6.937460716530484e-06,
+      "loss": 1.0753,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9819967266775778,
+      "grad_norm": 16.970993041992188,
+      "learning_rate": 6.780326838466373e-06,
+      "loss": 1.068,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0287584755669863,
+      "grad_norm": 0.7194657921791077,
+      "learning_rate": 6.623192960402264e-06,
+      "loss": 1.0816,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0755202244563946,
+      "grad_norm": 0.8986325860023499,
+      "learning_rate": 6.467630421118794e-06,
+      "loss": 1.0516,
+      "step": 2300
+    },
+    {
+      "epoch": 1.1222819733458032,
+      "grad_norm": 0.8846977353096008,
+      "learning_rate": 6.3104965430546826e-06,
+      "loss": 1.0775,
+      "step": 2400
+    },
+    {
+      "epoch": 1.1690437222352117,
+      "grad_norm": 0.8062325119972229,
+      "learning_rate": 6.153362664990572e-06,
+      "loss": 1.0796,
+      "step": 2500
+    },
+    {
+      "epoch": 1.21580547112462,
+      "grad_norm": 9.224539756774902,
+      "learning_rate": 5.996228786926462e-06,
+      "loss": 1.0646,
+      "step": 2600
+    },
+    {
+      "epoch": 1.2625672200140285,
+      "grad_norm": 0.7716740369796753,
+      "learning_rate": 5.839094908862352e-06,
+      "loss": 1.0699,
+      "step": 2700
+    },
+    {
+      "epoch": 1.3093289689034369,
+      "grad_norm": 1.1291840076446533,
+      "learning_rate": 5.681961030798241e-06,
+      "loss": 1.0679,
+      "step": 2800
+    },
+    {
+      "epoch": 1.3560907177928454,
+      "grad_norm": 1.0691558122634888,
+      "learning_rate": 5.5248271527341305e-06,
+      "loss": 1.0871,
+      "step": 2900
+    },
+    {
+      "epoch": 1.402852466682254,
+      "grad_norm": 1.0153058767318726,
+      "learning_rate": 5.367693274670019e-06,
+      "loss": 1.0418,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4496142155716623,
+      "grad_norm": 0.8397168517112732,
+      "learning_rate": 5.210559396605908e-06,
+      "loss": 1.0751,
+      "step": 3100
+    },
+    {
+      "epoch": 1.4963759644610708,
+      "grad_norm": 0.9355253577232361,
+      "learning_rate": 5.053425518541798e-06,
+      "loss": 1.0588,
+      "step": 3200
+    },
+    {
+      "epoch": 1.5431377133504793,
+      "grad_norm": 0.9902454614639282,
+      "learning_rate": 4.896291640477687e-06,
+      "loss": 1.0847,
+      "step": 3300
+    },
+    {
+      "epoch": 1.5898994622398877,
+      "grad_norm": 0.9210862517356873,
+      "learning_rate": 4.739157762413577e-06,
+      "loss": 1.076,
+      "step": 3400
+    },
+    {
+      "epoch": 1.6366612111292962,
+      "grad_norm": 0.9090029001235962,
+      "learning_rate": 4.5820238843494665e-06,
+      "loss": 1.0579,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6834229600187047,
+      "grad_norm": 0.9450795650482178,
+      "learning_rate": 4.424890006285355e-06,
+      "loss": 1.079,
+      "step": 3600
+    },
+    {
+      "epoch": 1.730184708908113,
+      "grad_norm": 0.8659577965736389,
+      "learning_rate": 4.267756128221245e-06,
+      "loss": 1.0583,
+      "step": 3700
+    },
+    {
+      "epoch": 1.7769464577975216,
+      "grad_norm": 0.9201979041099548,
+      "learning_rate": 4.110622250157134e-06,
+      "loss": 1.0263,
+      "step": 3800
+    },
+    {
+      "epoch": 1.8237082066869301,
+      "grad_norm": 1.2461769580841064,
+      "learning_rate": 3.953488372093024e-06,
+      "loss": 1.0579,
+      "step": 3900
+    },
+    {
+      "epoch": 1.8704699555763384,
+      "grad_norm": 0.8340646028518677,
+      "learning_rate": 3.796354494028913e-06,
+      "loss": 1.0781,
+      "step": 4000
+    },
+    {
+      "epoch": 1.917231704465747,
+      "grad_norm": 1.7858061790466309,
+      "learning_rate": 3.6392206159648025e-06,
+      "loss": 1.0701,
+      "step": 4100
+    },
+    {
+      "epoch": 1.9639934533551555,
+      "grad_norm": 1.354982614517212,
+      "learning_rate": 3.4820867379006918e-06,
+      "loss": 1.0613,
+      "step": 4200
+    },
+    {
+      "epoch": 2.010755202244564,
+      "grad_norm": 0.9671053886413574,
+      "learning_rate": 3.324952859836581e-06,
+      "loss": 1.0741,
+      "step": 4300
+    },
+    {
+      "epoch": 2.0575169511339726,
+      "grad_norm": 0.8994483351707458,
+      "learning_rate": 3.1678189817724704e-06,
+      "loss": 1.0347,
+      "step": 4400
+    },
+    {
+      "epoch": 2.104278700023381,
+      "grad_norm": 1.036387324333191,
+      "learning_rate": 3.0106851037083594e-06,
+      "loss": 1.054,
+      "step": 4500
+    },
+    {
+      "epoch": 2.1510404489127892,
+      "grad_norm": 1.0670599937438965,
+      "learning_rate": 2.8535512256442495e-06,
+      "loss": 1.0315,
+      "step": 4600
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 1.0409014225006104,
+      "learning_rate": 2.6964173475801384e-06,
+      "loss": 1.0626,
+      "step": 4700
+    },
+    {
+      "epoch": 2.2445639466916063,
+      "grad_norm": 1.0264023542404175,
+      "learning_rate": 2.5392834695160278e-06,
+      "loss": 1.0352,
+      "step": 4800
+    },
+    {
+      "epoch": 2.2913256955810146,
+      "grad_norm": 3.9457595348358154,
+      "learning_rate": 2.382149591451917e-06,
+      "loss": 1.0428,
+      "step": 4900
+    },
+    {
+      "epoch": 2.3380874444704234,
+      "grad_norm": 0.966581404209137,
+      "learning_rate": 2.225015713387807e-06,
+      "loss": 1.0487,
+      "step": 5000
+    },
+    {
+      "epoch": 2.3848491933598317,
+      "grad_norm": 1.0433825254440308,
+      "learning_rate": 2.0678818353236958e-06,
+      "loss": 1.0679,
+      "step": 5100
+    },
+    {
+      "epoch": 2.43161094224924,
+      "grad_norm": 1.005495548248291,
+      "learning_rate": 1.910747957259585e-06,
+      "loss": 1.0497,
+      "step": 5200
+    },
+    {
+      "epoch": 2.4783726911386488,
+      "grad_norm": 1.0041530132293701,
+      "learning_rate": 1.7536140791954748e-06,
+      "loss": 1.05,
+      "step": 5300
+    },
+    {
+      "epoch": 2.525134440028057,
+      "grad_norm": 1.108376383781433,
+      "learning_rate": 1.596480201131364e-06,
+      "loss": 1.0618,
+      "step": 5400
+    },
+    {
+      "epoch": 2.5718961889174654,
+      "grad_norm": 1.0034010410308838,
+      "learning_rate": 1.4393463230672533e-06,
+      "loss": 1.0486,
+      "step": 5500
+    },
+    {
+      "epoch": 2.6186579378068737,
+      "grad_norm": 0.9590221047401428,
+      "learning_rate": 1.2822124450031428e-06,
+      "loss": 1.0514,
+      "step": 5600
+    },
+    {
+      "epoch": 2.6654196866962825,
+      "grad_norm": 1.027959942817688,
+      "learning_rate": 1.1250785669390322e-06,
+      "loss": 1.0578,
+      "step": 5700
+    },
+    {
+      "epoch": 2.712181435585691,
+      "grad_norm": 0.9596933722496033,
+      "learning_rate": 9.679446888749215e-07,
+      "loss": 1.0659,
+      "step": 5800
+    },
+    {
+      "epoch": 2.7589431844750996,
+      "grad_norm": 1.142251968383789,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 1.0714,
+      "step": 5900
+    },
+    {
+      "epoch": 2.805704933364508,
+      "grad_norm": 1.2584409713745117,
+      "learning_rate": 6.536769327467001e-07,
+      "loss": 1.0485,
+      "step": 6000
+    },
+    {
+      "epoch": 2.852466682253916,
+      "grad_norm": 1.3494170904159546,
+      "learning_rate": 4.965430546825896e-07,
+      "loss": 1.0321,
+      "step": 6100
+    },
+    {
+      "epoch": 2.8992284311433245,
+      "grad_norm": 0.9571290612220764,
+      "learning_rate": 3.39409176618479e-07,
+      "loss": 1.0181,
+      "step": 6200
+    },
+    {
+      "epoch": 2.9459901800327333,
+      "grad_norm": 1.231972575187683,
+      "learning_rate": 1.8227529855436833e-07,
+      "loss": 1.0409,
+      "step": 6300
+    },
+    {
+      "epoch": 2.9927519289221416,
+      "grad_norm": 2.6358070373535156,
+      "learning_rate": 2.6712759270898807e-08,
+      "loss": 1.048,
+      "step": 6400
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2138,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.481950171724329e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbaba62cf254a6779e4b0b59f028ca6fe1850ad43b5ee6e8ddcb9c0343690b44
+size 5048