EshAhm/LoRa-Python1

README.md

@@ -0,0 +1,85 @@
+---
+library_name: peft
+license: mit
+base_model: microsoft/phi-2
+tags:
+- base_model:adapter:microsoft/phi-2
+- lora
+pipeline_tag: text-generation
+model-index:
+- name: phi-2-LoRa-Python
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# phi-2-LoRa-Python
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.4689
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.5284        | 0.1333 | 100  | 4.4728          |
+| 4.4172        | 0.2667 | 200  | 4.4776          |
+| 4.2789        | 0.4    | 300  | 4.4774          |
+| 4.4041        | 0.5333 | 400  | 4.4751          |
+| 4.3978        | 0.6667 | 500  | 4.4777          |
+| 4.061         | 0.8    | 600  | 4.4762          |
+| 4.1693        | 0.9333 | 700  | 4.4764          |
+| 4.5403        | 1.0667 | 800  | 4.4727          |
+| 4.5481        | 1.2    | 900  | 4.4725          |
+| 4.0223        | 1.3333 | 1000 | 4.4757          |
+| 4.5108        | 1.4667 | 1100 | 4.4747          |
+| 4.0763        | 1.6    | 1200 | 4.4719          |
+| 4.1443        | 1.7333 | 1300 | 4.4723          |
+| 4.4699        | 1.8667 | 1400 | 4.4738          |
+| 4.7084        | 2.0    | 1500 | 4.4713          |
+| 3.9716        | 2.1333 | 1600 | 4.4710          |
+| 4.5229        | 2.2667 | 1700 | 4.4711          |
+| 3.8189        | 2.4    | 1800 | 4.4702          |
+| 4.6479        | 2.5333 | 1900 | 4.4695          |
+| 4.4305        | 2.6667 | 2000 | 4.4690          |
+| 4.2955        | 2.8    | 2100 | 4.4690          |
+| 4.2989        | 2.9333 | 2200 | 4.4689          |
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "dense",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2746cc7bdcac3d6b58df64efac21ef3160762157b0ea2c2af8976c80df4b6ef8
+size 83924816

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a7985546e2331302690dc943aa4032cf03d6e8a512705d41ba11c33fac01ec
+size 5777