Upload 5 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/phi-2
+---
+
+# 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 +1,33 @@
+{
+  "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": 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": [
+    "v_proj",
+    "dense",
+    "q_proj",
+    "k_proj",
+    "fc1",
+    "fc2"
+  ],
+  "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 sha256:6210a483394f694ab6595bcf4ba75b8d62eb474781e02c56a23a17642382d26e
+size 47235968

trainer_state.json

@@ -0,0 +1,423 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.2585286796092987,
+      "learning_rate": 0.0001,
+      "loss": 0.9729,
+      "step": 5
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 0.3368561565876007,
+      "learning_rate": 0.0002,
+      "loss": 0.9899,
+      "step": 10
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 0.499980092048645,
+      "learning_rate": 0.00019583333333333334,
+      "loss": 0.7853,
+      "step": 15
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.3696683347225189,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 0.6654,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.40797653794288635,
+      "learning_rate": 0.0001875,
+      "loss": 0.6311,
+      "step": 25
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.33503052592277527,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.6248,
+      "step": 30
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 0.3338172733783722,
+      "learning_rate": 0.0001791666666666667,
+      "loss": 0.6046,
+      "step": 35
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.3330083191394806,
+      "learning_rate": 0.000175,
+      "loss": 0.6173,
+      "step": 40
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 0.3610495328903198,
+      "learning_rate": 0.00017083333333333333,
+      "loss": 0.6598,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.5117771625518799,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.701,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 0.5943231582641602,
+      "eval_runtime": 1078.9543,
+      "eval_samples_per_second": 5.423,
+      "eval_steps_per_second": 0.678,
+      "step": 50
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 0.24727080762386322,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.5523,
+      "step": 55
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.32829391956329346,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 0.5601,
+      "step": 60
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 0.2365810126066208,
+      "learning_rate": 0.00015416666666666668,
+      "loss": 0.5529,
+      "step": 65
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.23763389885425568,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5683,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.2370971143245697,
+      "learning_rate": 0.00014583333333333335,
+      "loss": 0.5734,
+      "step": 75
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.23187637329101562,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 0.5589,
+      "step": 80
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 0.2783190906047821,
+      "learning_rate": 0.0001375,
+      "loss": 0.5833,
+      "step": 85
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.2846642732620239,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.5855,
+      "step": 90
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 0.30239176750183105,
+      "learning_rate": 0.00012916666666666667,
+      "loss": 0.6083,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4522075057029724,
+      "learning_rate": 0.000125,
+      "loss": 0.6666,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.5652860403060913,
+      "eval_runtime": 1078.4557,
+      "eval_samples_per_second": 5.425,
+      "eval_steps_per_second": 0.679,
+      "step": 100
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.34593072533607483,
+      "learning_rate": 0.00012083333333333333,
+      "loss": 0.5283,
+      "step": 105
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.24053940176963806,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.5376,
+      "step": 110
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.25374647974967957,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 0.5268,
+      "step": 115
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.2413879930973053,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 0.5466,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.22842754423618317,
+      "learning_rate": 0.00010416666666666667,
+      "loss": 0.558,
+      "step": 125
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.23777280747890472,
+      "learning_rate": 0.0001,
+      "loss": 0.5304,
+      "step": 130
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.2853969633579254,
+      "learning_rate": 9.583333333333334e-05,
+      "loss": 0.5773,
+      "step": 135
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.28491005301475525,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 0.5898,
+      "step": 140
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.3216317892074585,
+      "learning_rate": 8.75e-05,
+      "loss": 0.6376,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.47678303718566895,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.6448,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.5443492531776428,
+      "eval_runtime": 1078.9513,
+      "eval_samples_per_second": 5.423,
+      "eval_steps_per_second": 0.678,
+      "step": 150
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.3121783435344696,
+      "learning_rate": 7.916666666666666e-05,
+      "loss": 0.5081,
+      "step": 155
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.2449740618467331,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.511,
+      "step": 160
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.2097545564174652,
+      "learning_rate": 7.083333333333334e-05,
+      "loss": 0.509,
+      "step": 165
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.23882268369197845,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5411,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.26276838779449463,
+      "learning_rate": 6.25e-05,
+      "loss": 0.5539,
+      "step": 175
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.26204946637153625,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.5692,
+      "step": 180
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.27385151386260986,
+      "learning_rate": 5.4166666666666664e-05,
+      "loss": 0.5599,
+      "step": 185
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.3151029646396637,
+      "learning_rate": 5e-05,
+      "loss": 0.5622,
+      "step": 190
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.372055321931839,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.6128,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4943559765815735,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6352,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.5273013114929199,
+      "eval_runtime": 1079.0525,
+      "eval_samples_per_second": 5.422,
+      "eval_steps_per_second": 0.678,
+      "step": 200
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.28252649307250977,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4963,
+      "step": 205
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.2909074127674103,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5165,
+      "step": 210
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.2641913890838623,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.5264,
+      "step": 215
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.2438758909702301,
+      "learning_rate": 2.5e-05,
+      "loss": 0.525,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2509464621543884,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.5451,
+      "step": 225
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.26488572359085083,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5512,
+      "step": 230
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.2820191979408264,
+      "learning_rate": 1.25e-05,
+      "loss": 0.548,
+      "step": 235
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.3010896146297455,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.578,
+      "step": 240
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.38558459281921387,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.5913,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6697375178337097,
+      "learning_rate": 0.0,
+      "loss": 0.6351,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.5142252445220947,
+      "eval_runtime": 1078.9757,
+      "eval_samples_per_second": 5.423,
+      "eval_steps_per_second": 0.678,
+      "step": 250
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.64628687263744e+16,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdbb904a0de0d0bedb04b1076d8999b0f53936b7c462eda048ac804b925cd33
+size 5048