MultiPRIDE-DualEncoder-LPFT-es

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+base_model: cardiffnlp/twitter-xlm-roberta-base-hate-spanish
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: MultiPRIDE-DualEncoder-LPFT-es
+  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-es
+
+This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-hate-spanish](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-hate-spanish) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4688
+- Accuracy: 0.8030
+- F1: 0.5667
+- Precision: 0.425
+- Recall: 0.85
+
+## 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: 42
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.6778        | 1.0   | 77   | 0.5634          | 0.8030   | 0.5    | 0.4062    | 0.65   |
+| 0.6517        | 2.0   | 154  | 0.5011          | 0.7273   | 0.4706 | 0.3333    | 0.8    |
+| 0.6283        | 3.0   | 231  | 0.5121          | 0.7727   | 0.5312 | 0.3864    | 0.85   |
+| 0.6041        | 4.0   | 308  | 0.4802          | 0.8182   | 0.5862 | 0.4474    | 0.85   |
+| 0.6153        | 5.0   | 385  | 0.4840          | 0.7879   | 0.5484 | 0.4048    | 0.85   |
+| 0.5638        | 6.0   | 462  | 0.4761          | 0.7803   | 0.5397 | 0.3953    | 0.85   |
+| 0.5421        | 7.0   | 539  | 0.4688          | 0.8030   | 0.5667 | 0.425     | 0.85   |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "DualEncoderForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "class_weights": [
+    1.179190754890442,
+    6.5806450843811035
+  ],
+  "classifier_dropout": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOT-HATE",
+    "1": "HATE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "HATE": 1,
+    "NOT-HATE": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c472ac76e5c4182a3cd811015cef848f3ab4b3bc1a5da9bc99aef0e382d792
+size 1115770572

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6123d693a1672038386f5e9b4f0e796cc99675ffe4689b05d78b53f69fe8dbc9
+size 5969