Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-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 0.7.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4fea086c1f6f96126f66ce6a89be7bc027097705a072013ed21bb9388238a0
+size 35668592

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97aebff48304ef32e27aee4747d4a236e927f04dc7c755f93d2558839374ef28
+size 18009786

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abfaabaed1654a43b21011670754dff8d4de5330cac46d21ef12dff10cd6351
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf72ff674c4d7b184c8aa1b2af572e0aa537a40db0cf8ad80bb97ff5eb161408
+size 1064

trainer_state.json

@@ -0,0 +1,231 @@
+{
+  "best_metric": 0.19941402971744537,
+  "best_model_checkpoint": "/kaggle/working/trainer/checkpoint-590",
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 1770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.8408871745419484e-05,
+      "loss": 2.902,
+      "step": 118
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.314755380153656,
+      "eval_runtime": 19.7216,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 118
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.563645130183221e-05,
+      "loss": 0.3101,
+      "step": 236
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8408044576644897,
+      "eval_runtime": 19.716,
+      "eval_samples_per_second": 1.319,
+      "eval_steps_per_second": 0.659,
+      "step": 236
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.2960462873674064e-05,
+      "loss": 1.0237,
+      "step": 354
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.23988741636276245,
+      "eval_runtime": 19.7335,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 354
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.011571841851495e-05,
+      "loss": 0.3245,
+      "step": 472
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.20902396738529205,
+      "eval_runtime": 19.6909,
+      "eval_samples_per_second": 1.32,
+      "eval_steps_per_second": 0.66,
+      "step": 472
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.7270973963355835e-05,
+      "loss": 0.1679,
+      "step": 590
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19941402971744537,
+      "eval_runtime": 19.7266,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 590
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.442622950819672e-05,
+      "loss": 0.1973,
+      "step": 708
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.21409890055656433,
+      "eval_runtime": 19.7603,
+      "eval_samples_per_second": 1.316,
+      "eval_steps_per_second": 0.658,
+      "step": 708
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.158148505303761e-05,
+      "loss": 0.2323,
+      "step": 826
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.2766213119029999,
+      "eval_runtime": 19.7249,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 826
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.87367405978785e-05,
+      "loss": 0.2064,
+      "step": 944
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.20961548388004303,
+      "eval_runtime": 19.7074,
+      "eval_samples_per_second": 1.319,
+      "eval_steps_per_second": 0.66,
+      "step": 944
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.589199614271938e-05,
+      "loss": 0.1943,
+      "step": 1062
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.2783980965614319,
+      "eval_runtime": 19.7328,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 1062
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.304725168756027e-05,
+      "loss": 0.2605,
+      "step": 1180
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.28063008189201355,
+      "eval_runtime": 19.721,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 1180
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.020250723240116e-05,
+      "loss": 0.2797,
+      "step": 1298
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.7226824164390564,
+      "eval_runtime": 19.7144,
+      "eval_samples_per_second": 1.319,
+      "eval_steps_per_second": 0.659,
+      "step": 1298
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1.7357762777242045e-05,
+      "loss": 0.5877,
+      "step": 1416
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.3170361816883087,
+      "eval_runtime": 19.7302,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 1416
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 1.4513018322082934e-05,
+      "loss": 0.3059,
+      "step": 1534
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.24836881458759308,
+      "eval_runtime": 19.6883,
+      "eval_samples_per_second": 1.321,
+      "eval_steps_per_second": 0.66,
+      "step": 1534
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 1.166827386692382e-05,
+      "loss": 0.1948,
+      "step": 1652
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.25250551104545593,
+      "eval_runtime": 19.7516,
+      "eval_samples_per_second": 1.316,
+      "eval_steps_per_second": 0.658,
+      "step": 1652
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.1966,
+      "step": 1770
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.21671946346759796,
+      "eval_runtime": 19.7256,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.659,
+      "step": 1770
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2124,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 18,
+  "save_steps": 500,
+  "total_flos": 3.242923135598592e+17,
+  "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 sha256:5520bbc5f9d333e3b04e3f5b73b40d950e18d6c05ca69a9b27f17e1859e2fb94
+size 4728