brenomatos/distilbert-base-multilingual-cased

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: distilbert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: distilbert-base-multilingual-cased
+  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-multilingual-cased
+
+This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0472
+- Accuracy: 0.9936
+- F1: 0.9936
+
+## 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: 64
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.1749        | 1.0   | 1094 | 0.0427          | 0.9935   | 0.9935 |
+| 0.006         | 2.0   | 2188 | 0.0421          | 0.9936   | 0.9936 |
+| 0.0023        | 3.0   | 3282 | 0.0472          | 0.9936   | 0.9936 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "ar",
+    "1": "bg",
+    "2": "de",
+    "3": "el",
+    "4": "en",
+    "5": "es",
+    "6": "fr",
+    "7": "hi",
+    "8": "it",
+    "9": "ja",
+    "10": "nl",
+    "11": "pl",
+    "12": "pt",
+    "13": "ru",
+    "14": "sw",
+    "15": "th",
+    "16": "tr",
+    "17": "ur",
+    "18": "vi",
+    "19": "zh"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "ar": 0,
+    "bg": 1,
+    "de": 2,
+    "el": 3,
+    "en": 4,
+    "es": 5,
+    "fr": 6,
+    "hi": 7,
+    "it": 8,
+    "ja": 9,
+    "nl": 10,
+    "pl": 11,
+    "pt": 12,
+    "ru": 13,
+    "sw": 14,
+    "th": 15,
+    "tr": 16,
+    "ur": 17,
+    "vi": 18,
+    "zh": 19
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fb29d2c99b8b42c69d52905d96d1e58b7c5840e2a34c606c834b9ed6cb9496
+size 541372744

runs/Jan20_14-18-32_4f99bf91cef0/events.out.tfevents.1705760313.4f99bf91cef0.27012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604377dc34c269a69109d9b6eb4c2be44ab902edace6a0937b05383ee616e85f
+size 6790

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "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 sha256:9fab081a0be10775098b709f7fef4a9649c432d048b4d79e7ab0f06f034451a2
+size 4664