Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# 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 0.13.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "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": 32,
+  "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",
+    "dense",
+    "q_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 sha256:8416235a191eab858af515f6619d5977a0b0a8d627b50950bd9f4b9d8ee458f6
+size 83920464

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367ff1289a5f73d75499021c1b5d4a9376e6ddb529240e80c5ed769dc533a215
+size 42900052

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57940070b0aebb332434cb45c62feca83511526dd762d8ddd7314ee75af004b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b5bf190dc871967c45091d9f1ab233b2d2ed62baca21fee5dfedb5718ffa5d
+size 1064

trainer_state.json

@@ -0,0 +1,329 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3337505214851898,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008343763037129746,
+      "grad_norm": 0.7562159895896912,
+      "learning_rate": 0.0001951951951951952,
+      "loss": 1.9181,
+      "step": 25
+    },
+    {
+      "epoch": 0.016687526074259492,
+      "grad_norm": 0.8098325133323669,
+      "learning_rate": 0.0001901901901901902,
+      "loss": 1.1849,
+      "step": 50
+    },
+    {
+      "epoch": 0.025031289111389236,
+      "grad_norm": 0.3777216374874115,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 1.6916,
+      "step": 75
+    },
+    {
+      "epoch": 0.033375052148518984,
+      "grad_norm": 0.5206697583198547,
+      "learning_rate": 0.00018018018018018018,
+      "loss": 1.1422,
+      "step": 100
+    },
+    {
+      "epoch": 0.041718815185648725,
+      "grad_norm": 0.38817787170410156,
+      "learning_rate": 0.0001751751751751752,
+      "loss": 1.6667,
+      "step": 125
+    },
+    {
+      "epoch": 0.05006257822277847,
+      "grad_norm": 0.6388385891914368,
+      "learning_rate": 0.0001701701701701702,
+      "loss": 1.2033,
+      "step": 150
+    },
+    {
+      "epoch": 0.05840634125990822,
+      "grad_norm": 0.4120958149433136,
+      "learning_rate": 0.00016516516516516518,
+      "loss": 1.725,
+      "step": 175
+    },
+    {
+      "epoch": 0.06675010429703797,
+      "grad_norm": 0.46837368607521057,
+      "learning_rate": 0.00016016016016016018,
+      "loss": 1.065,
+      "step": 200
+    },
+    {
+      "epoch": 0.07509386733416772,
+      "grad_norm": 0.4679395854473114,
+      "learning_rate": 0.00015515515515515516,
+      "loss": 1.7601,
+      "step": 225
+    },
+    {
+      "epoch": 0.08343763037129745,
+      "grad_norm": 0.380135178565979,
+      "learning_rate": 0.00015015015015015014,
+      "loss": 1.0251,
+      "step": 250
+    },
+    {
+      "epoch": 0.0917813934084272,
+      "grad_norm": 0.3675175905227661,
+      "learning_rate": 0.00014514514514514515,
+      "loss": 1.6459,
+      "step": 275
+    },
+    {
+      "epoch": 0.10012515644555695,
+      "grad_norm": 0.48725131154060364,
+      "learning_rate": 0.00014014014014014013,
+      "loss": 1.0373,
+      "step": 300
+    },
+    {
+      "epoch": 0.1084689194826867,
+      "grad_norm": 0.42459967732429504,
+      "learning_rate": 0.00013513513513513514,
+      "loss": 1.6939,
+      "step": 325
+    },
+    {
+      "epoch": 0.11681268251981644,
+      "grad_norm": 0.44615626335144043,
+      "learning_rate": 0.00013013013013013014,
+      "loss": 1.1265,
+      "step": 350
+    },
+    {
+      "epoch": 0.1251564455569462,
+      "grad_norm": 0.3729555904865265,
+      "learning_rate": 0.00012512512512512512,
+      "loss": 1.7411,
+      "step": 375
+    },
+    {
+      "epoch": 0.13350020859407594,
+      "grad_norm": 0.42633363604545593,
+      "learning_rate": 0.00012012012012012013,
+      "loss": 1.1436,
+      "step": 400
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 0.4313684105873108,
+      "learning_rate": 0.00011511511511511512,
+      "loss": 1.6521,
+      "step": 425
+    },
+    {
+      "epoch": 0.15018773466833543,
+      "grad_norm": 0.3195270597934723,
+      "learning_rate": 0.00011011011011011012,
+      "loss": 0.984,
+      "step": 450
+    },
+    {
+      "epoch": 0.15853149770546515,
+      "grad_norm": 0.279301255941391,
+      "learning_rate": 0.00010510510510510511,
+      "loss": 1.6523,
+      "step": 475
+    },
+    {
+      "epoch": 0.1668752607425949,
+      "grad_norm": 0.32661929726600647,
+      "learning_rate": 0.00010010010010010012,
+      "loss": 1.0151,
+      "step": 500
+    },
+    {
+      "epoch": 0.1668752607425949,
+      "eval_loss": 1.5524340867996216,
+      "eval_runtime": 511.702,
+      "eval_samples_per_second": 2.931,
+      "eval_steps_per_second": 0.367,
+      "step": 500
+    },
+    {
+      "epoch": 0.17521902377972465,
+      "grad_norm": 0.27320751547813416,
+      "learning_rate": 9.50950950950951e-05,
+      "loss": 1.6524,
+      "step": 525
+    },
+    {
+      "epoch": 0.1835627868168544,
+      "grad_norm": 0.393206387758255,
+      "learning_rate": 9.009009009009009e-05,
+      "loss": 0.9658,
+      "step": 550
+    },
+    {
+      "epoch": 0.19190654985398414,
+      "grad_norm": 0.29037702083587646,
+      "learning_rate": 8.50850850850851e-05,
+      "loss": 1.6467,
+      "step": 575
+    },
+    {
+      "epoch": 0.2002503128911139,
+      "grad_norm": 0.3599018156528473,
+      "learning_rate": 8.008008008008009e-05,
+      "loss": 1.0368,
+      "step": 600
+    },
+    {
+      "epoch": 0.20859407592824364,
+      "grad_norm": 0.397064208984375,
+      "learning_rate": 7.507507507507507e-05,
+      "loss": 1.7412,
+      "step": 625
+    },
+    {
+      "epoch": 0.2169378389653734,
+      "grad_norm": 0.3856523334980011,
+      "learning_rate": 7.007007007007007e-05,
+      "loss": 1.1053,
+      "step": 650
+    },
+    {
+      "epoch": 0.22528160200250313,
+      "grad_norm": 0.30977582931518555,
+      "learning_rate": 6.506506506506507e-05,
+      "loss": 1.7623,
+      "step": 675
+    },
+    {
+      "epoch": 0.23362536503963288,
+      "grad_norm": 0.4029249846935272,
+      "learning_rate": 6.0060060060060066e-05,
+      "loss": 1.1681,
+      "step": 700
+    },
+    {
+      "epoch": 0.24196912807676263,
+      "grad_norm": 0.3093183636665344,
+      "learning_rate": 5.505505505505506e-05,
+      "loss": 1.7267,
+      "step": 725
+    },
+    {
+      "epoch": 0.2503128911138924,
+      "grad_norm": 0.45136523246765137,
+      "learning_rate": 5.005005005005006e-05,
+      "loss": 1.1256,
+      "step": 750
+    },
+    {
+      "epoch": 0.2586566541510221,
+      "grad_norm": 0.2787851393222809,
+      "learning_rate": 4.5045045045045046e-05,
+      "loss": 1.7174,
+      "step": 775
+    },
+    {
+      "epoch": 0.2670004171881519,
+      "grad_norm": 0.33277878165245056,
+      "learning_rate": 4.0040040040040046e-05,
+      "loss": 0.9848,
+      "step": 800
+    },
+    {
+      "epoch": 0.2753441802252816,
+      "grad_norm": 0.3014131784439087,
+      "learning_rate": 3.503503503503503e-05,
+      "loss": 1.6547,
+      "step": 825
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.27079567313194275,
+      "learning_rate": 3.0030030030030033e-05,
+      "loss": 1.1372,
+      "step": 850
+    },
+    {
+      "epoch": 0.2920317062995411,
+      "grad_norm": 0.2874036729335785,
+      "learning_rate": 2.502502502502503e-05,
+      "loss": 1.7384,
+      "step": 875
+    },
+    {
+      "epoch": 0.30037546933667086,
+      "grad_norm": 0.38741400837898254,
+      "learning_rate": 2.0020020020020023e-05,
+      "loss": 1.0731,
+      "step": 900
+    },
+    {
+      "epoch": 0.3087192323738006,
+      "grad_norm": 0.3522486090660095,
+      "learning_rate": 1.5015015015015016e-05,
+      "loss": 1.6537,
+      "step": 925
+    },
+    {
+      "epoch": 0.3170629954109303,
+      "grad_norm": 0.41225603222846985,
+      "learning_rate": 1.0010010010010011e-05,
+      "loss": 1.0646,
+      "step": 950
+    },
+    {
+      "epoch": 0.32540675844806005,
+      "grad_norm": 0.33286789059638977,
+      "learning_rate": 5.005005005005006e-06,
+      "loss": 1.6279,
+      "step": 975
+    },
+    {
+      "epoch": 0.3337505214851898,
+      "grad_norm": 0.405441552400589,
+      "learning_rate": 0.0,
+      "loss": 1.0594,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3337505214851898,
+      "eval_loss": 1.5415141582489014,
+      "eval_runtime": 511.169,
+      "eval_samples_per_second": 2.934,
+      "eval_steps_per_second": 0.368,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.341797200653312e+16,
+  "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 sha256:8664ef8fa8cdfee0851daa8a862bb59831c5f962a3f8a2c2cd11b610391e69e2
+size 5176