HatePhi-2

README.md

@@ -0,0 +1,91 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: hate-phi
+  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. -->
+
+# hate-phi
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2799
+- Classification Report:               precision    recall  f1-score   support
+
+           0       0.50      0.23      0.32       422
+           1       0.92      0.96      0.94      5753
+           2       0.84      0.85      0.85      1260
+
+    accuracy                           0.90      7435
+   macro avg       0.75      0.68      0.70      7435
+weighted avg       0.89      0.90      0.89      7435
+
+
+## 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: 64
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Classification Report                                                                                                                                                                                                                                                                                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| 0.6124        | 0.37  | 25   | 0.3696          |               precision    recall  f1-score   support
+
+           0       0.44      0.03      0.05       422
+           1       0.90      0.95      0.93      5753
+           2       0.74      0.79      0.76      1260
+
+    accuracy                           0.87      7435
+   macro avg       0.70      0.59      0.58      7435
+weighted avg       0.85      0.87      0.85      7435
+ |
+| 0.3268        | 0.74  | 50   | 0.2900          |               precision    recall  f1-score   support
+
+           0       0.50      0.16      0.25       422
+           1       0.92      0.96      0.94      5753
+           2       0.82      0.85      0.84      1260
+
+    accuracy                           0.89      7435
+   macro avg       0.75      0.66      0.67      7435
+weighted avg       0.88      0.89      0.88      7435
+ |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 1,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "dense"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf6c03f8d38720ddd510193289fda367ae521b296d349a80ef51bd8c70dbec1
+size 2685728

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a95f4c0554d02f48c1eba55025c6e50787e0892864c74e4d9570d3aac742a8
+size 4856