MultiPRIDE-DualEncoder-LPFT-it

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: nickprock/setfit-italian-hate-speech
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: MultiPRIDE-DualEncoder-LPFT-it
+  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. -->
+
+# MultiPRIDE-DualEncoder-LPFT-it
+
+This model is a fine-tuned version of [nickprock/setfit-italian-hate-speech](https://huggingface.co/nickprock/setfit-italian-hate-speech) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0215
+- Accuracy: 0.9202
+- F1: 0.8060
+- Precision: 0.75
+- Recall: 0.8710
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 67
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1723        | 1.0   | 95   | 0.1277          | 0.8037   | 0.5556 | 0.4878    | 0.6452 |
+| 0.1278        | 2.0   | 190  | 0.0812          | 0.9325   | 0.8    | 0.9167    | 0.7097 |
+| 0.0705        | 3.0   | 285  | 0.0408          | 0.9571   | 0.8889 | 0.875     | 0.9032 |
+| 0.0463        | 4.0   | 380  | 0.0261          | 0.9509   | 0.8788 | 0.8286    | 0.9355 |
+| 0.0329        | 5.0   | 475  | 0.0216          | 0.9325   | 0.8406 | 0.7632    | 0.9355 |
+| 0.0237        | 6.0   | 570  | 0.0215          | 0.9202   | 0.8060 | 0.75      | 0.8710 |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "DualEncoderForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "class_weights": [
+    1.2357723712921143,
+    5.241379261016846
+  ],
+  "classifier_dropout": null,
+  "dtype": "bfloat16",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db58f5528513fa385e4a216aaaaa35589b6fc16c9f0ab91cfe8a9bfba73f2517
+size 443306324

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f01f330d70b201e4fb82602ae039e7a2d904076f32c955bcb83866e1127321
+size 5969