amitca71/marabert2-levantine-hate-model

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+base_model: UBC-NLP/MARBERTv2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: marbert_frozen_final
+  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. -->
+
+# marbert_frozen_final
+
+This model is a fine-tuned version of [UBC-NLP/MARBERTv2](https://huggingface.co/UBC-NLP/MARBERTv2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4863
+- Accuracy: 0.8404
+- F1 Macro: 0.7649
+
+## 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: 16
+- eval_batch_size: 32
+- seed: 42
+- 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
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| No log        | 1.0   | 398  | 0.5751          | 0.8153   | 0.7039   |
+| 0.6110        | 2.0   | 796  | 0.5615          | 0.8039   | 0.7199   |
+| 0.3777        | 3.0   | 1194 | 0.4863          | 0.8381   | 0.7632   |
+| 0.2827        | 4.0   | 1592 | 0.5130          | 0.8609   | 0.7924   |
+| 0.2827        | 5.0   | 1990 | 0.5780          | 0.8677   | 0.8048   |
+| 0.2192        | 6.0   | 2388 | 0.6634          | 0.8837   | 0.8271   |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,47 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Abusive",
+    "1": "Normal",
+    "2": "Hate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Abusive": 0,
+    "Hate": 2,
+    "Normal": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 100000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461b3da0fd0a8d075400c243690f7ebc022fc7a669936ed19794e1882967c8f4
+size 651398124

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060e5dda2352ad2d1e294dc4b0433c2db9efc57bf5c5e9375a5db4f3b0296f35
+size 5201