End of training

README.md

@@ -0,0 +1,104 @@
+---
+language:
+- ar
+library_name: peft
+tags:
+- generated_from_trainer
+datasets:
+- khalidalt/tydiqa-goldp
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2
+  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
+
+This model is a fine-tuned version of [microsoftl](https://huggingface.co/microsoftl) on the khalidalt/tydiqa-goldp dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1016
+
+## 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: 2.5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7708        | 0.02  | 50   | 1.5184          |
+| 1.4903        | 0.04  | 100  | 1.2735          |
+| 1.3474        | 0.06  | 150  | 1.2167          |
+| 1.3178        | 0.08  | 200  | 1.1864          |
+| 1.2963        | 0.1   | 250  | 1.1750          |
+| 1.2671        | 0.12  | 300  | 1.1676          |
+| 1.2484        | 0.14  | 350  | 1.1597          |
+| 1.2797        | 0.16  | 400  | 1.1546          |
+| 1.3196        | 0.18  | 450  | 1.1495          |
+| 1.2881        | 0.2   | 500  | 1.1435          |
+| 1.2389        | 0.22  | 550  | 1.1416          |
+| 1.2489        | 0.24  | 600  | 1.1371          |
+| 1.2223        | 0.26  | 650  | 1.1339          |
+| 1.2012        | 0.28  | 700  | 1.1307          |
+| 1.2285        | 0.3   | 750  | 1.1285          |
+| 1.255         | 0.32  | 800  | 1.1251          |
+| 1.2739        | 0.34  | 850  | 1.1229          |
+| 1.2412        | 0.36  | 900  | 1.1217          |
+| 1.2094        | 0.38  | 950  | 1.1204          |
+| 1.246         | 0.4   | 1000 | 1.1202          |
+| 1.1737        | 0.42  | 1050 | 1.1161          |
+| 1.2427        | 0.44  | 1100 | 1.1144          |
+| 1.2235        | 0.46  | 1150 | 1.1131          |
+| 1.2301        | 0.48  | 1200 | 1.1119          |
+| 1.1854        | 0.5   | 1250 | 1.1111          |
+| 1.1949        | 0.52  | 1300 | 1.1094          |
+| 1.243         | 0.54  | 1350 | 1.1088          |
+| 1.2121        | 0.56  | 1400 | 1.1081          |
+| 1.2124        | 0.58  | 1450 | 1.1081          |
+| 1.2065        | 0.6   | 1500 | 1.1061          |
+| 1.2357        | 0.62  | 1550 | 1.1058          |
+| 1.2253        | 0.64  | 1600 | 1.1050          |
+| 1.1751        | 0.66  | 1650 | 1.1034          |
+| 1.2171        | 0.68  | 1700 | 1.1042          |
+| 1.2091        | 0.7   | 1750 | 1.1038          |
+| 1.2111        | 0.72  | 1800 | 1.1027          |
+| 1.1808        | 0.74  | 1850 | 1.1023          |
+| 1.1233        | 0.76  | 1900 | 1.1020          |
+| 1.2327        | 0.78  | 1950 | 1.1020          |
+| 1.1534        | 0.8   | 2000 | 1.1016          |
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "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": [
+    "fc2",
+    "Wqkv",
+    "fc1"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd10889dadd087fa291436864ccdac17731c0dd6208b018f4dea2b697502500
+size 26230352

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170d2b4f2c9cdc6279d2c61d071af5acc95390892cc5d989ccbd02fd5053105a
+size 4664