Upload version gender_classifier_es_roberta_base

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+tags:
+- text-classification
+- modernbert
+- generated-data
+base_model: PeterPanecillo/PlanTL-GOB-ES-roberta-base-bne-copy
+metrics:
+- name: loss
+  type: loss
+  value: 0.42353931069374084
+- name: accuracy
+  type: accuracy
+  value: 0.905
+- name: f1
+  type: f1
+  value: 0.9049896921601716
+- name: precision
+  type: precision
+  value: 0.9049971109583139
+- name: recall
+  type: recall
+  value: 0.9049918871427097
+- name: runtime
+  type: runtime
+  value: 2.153
+- name: samples_per_second
+  type: samples_per_second
+  value: 2786.842
+- name: steps_per_second
+  type: steps_per_second
+  value: 43.661
+- name: epoch
+  type: epoch
+  value: 3.0
+---
+
+# Gender Classifier (Fine-tuned PeterPanecillo/PlanTL-GOB-ES-roberta-base-bne-copy)
+
+This model was fine-tuned to classify text into: male, female, neutral
+
+## Performance Metrics
+| Metric | Value |
+| :--- | :--- |
+| **loss** | 0.4235 |
+| **accuracy** | 0.9050 |
+| **f1** | 0.9050 |
+| **precision** | 0.9050 |
+| **recall** | 0.9050 |
+| **runtime** | 2.1530 |
+| **samples_per_second** | 2786.8420 |
+| **steps_per_second** | 43.6610 |
+| **epoch** | 3.0000 |
+
+## Hyperparameters
+- **Batch Size**: 64
+- **Learning Rate**: 5e-05
+- **Epochs**: 3
+- **Weight Decay**: 0.01
+- **Mixed Precision (FP16)**: True
+
+## Quick Usage
+```python
+from transformers import pipeline
+
+# Load the model directly from this folder or HF Hub
+classifier = pipeline('text-classification', model='.')
+print(classifier('She is a great engineer.'))
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "male",
+    "1": "female",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "female": 1,
+    "male": 0,
+    "neutral": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f171492c4ae6466dd06275109707daaa88dd6538722947132c9de7de5fff86e
+size 498606684

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ad1e92988137cc5c6cb070c645040f6fadde7c9fa672670d6fb2245030bbb1
+size 5905