chris32/bert-house_floor_levels-classification

README.md

@@ -0,0 +1,80 @@
+---
+base_model: dccuchile/distilbert-base-spanish-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: distilbert-base-spanish-uncased-finetuned-text-intelligence
+  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. -->
+
+# distilbert-base-spanish-uncased-finetuned-text-intelligence
+
+This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6945
+- Accuracy: 0.8834
+- F1: 0.8827
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 1.0148        | 1.0   | 235  | 0.7880          | 0.7138   | 0.6551 |
+| 0.6349        | 2.0   | 470  | 0.5415          | 0.8516   | 0.8500 |
+| 0.4709        | 3.0   | 705  | 0.4505          | 0.8587   | 0.8613 |
+| 0.3727        | 4.0   | 940  | 0.4156          | 0.8905   | 0.8900 |
+| 0.3163        | 5.0   | 1175 | 0.4262          | 0.8905   | 0.8910 |
+| 0.2695        | 6.0   | 1410 | 0.5090          | 0.8869   | 0.8874 |
+| 0.2332        | 7.0   | 1645 | 0.5014          | 0.8869   | 0.8865 |
+| 0.1811        | 8.0   | 1880 | 0.5735          | 0.8834   | 0.8827 |
+| 0.1542        | 9.0   | 2115 | 0.5626          | 0.8940   | 0.8932 |
+| 0.1192        | 10.0  | 2350 | 0.5680          | 0.8905   | 0.8900 |
+| 0.124         | 11.0  | 2585 | 0.6291          | 0.8869   | 0.8857 |
+| 0.0988        | 12.0  | 2820 | 0.6424          | 0.8834   | 0.8835 |
+| 0.0933        | 13.0  | 3055 | 0.7085          | 0.8693   | 0.8668 |
+| 0.0813        | 14.0  | 3290 | 0.6560          | 0.8905   | 0.8893 |
+| 0.0599        | 15.0  | 3525 | 0.7175          | 0.8799   | 0.8793 |
+| 0.0632        | 16.0  | 3760 | 0.6862          | 0.8799   | 0.8786 |
+| 0.0489        | 17.0  | 3995 | 0.7064          | 0.8869   | 0.8858 |
+| 0.0449        | 18.0  | 4230 | 0.7046          | 0.8834   | 0.8830 |
+| 0.039         | 19.0  | 4465 | 0.6997          | 0.8799   | 0.8790 |
+| 0.0388        | 20.0  | 4700 | 0.6945          | 0.8834   | 0.8827 |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.0
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 31002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285d06dd53c6d4e3029aabfe66fce2b1faa2af0914d3257a2bc779d12b03e6bc
+size 269313280

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b28c8f3299405e7bf3d72bf6ddeb0677dfdb18faf1e1d98ac4c99304fa93a4
+size 5048