Model save

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: fosh-detector-bert-v2.1-with-augmentation
+  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. -->
+
+# fosh-detector-bert-v2.1-with-augmentation
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0311
+- Accuracy: 0.9926
+- Precision: 0.9475
+- Recall: 0.9559
+- F1: 0.9517
+
+## 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: 5e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.2292        | 0.1639 | 50   | 0.1207          | 0.9669   | 0.8509    | 0.6882 | 0.7610 |
+| 0.0994        | 0.3279 | 100  | 0.0610          | 0.9775   | 0.8279    | 0.8912 | 0.8584 |
+| 0.0738        | 0.4918 | 150  | 0.0530          | 0.9863   | 0.9240    | 0.8941 | 0.9088 |
+| 0.0532        | 0.6557 | 200  | 0.0613          | 0.9788   | 0.7985    | 0.9676 | 0.875  |
+| 0.0436        | 0.8197 | 250  | 0.0346          | 0.9905   | 0.9382    | 0.9382 | 0.9382 |
+| 0.0375        | 0.9836 | 300  | 0.0440          | 0.9894   | 0.9222    | 0.9412 | 0.9316 |
+| 0.0362        | 1.1475 | 350  | 0.0383          | 0.9890   | 0.9053    | 0.9559 | 0.9299 |
+| 0.0265        | 1.3115 | 400  | 0.0348          | 0.9905   | 0.9233    | 0.9559 | 0.9393 |
+| 0.0286        | 1.4754 | 450  | 0.0374          | 0.9905   | 0.9331    | 0.9441 | 0.9386 |
+| 0.0247        | 1.6393 | 500  | 0.0298          | 0.9912   | 0.9388    | 0.9471 | 0.9429 |
+| 0.0327        | 1.8033 | 550  | 0.0297          | 0.9917   | 0.9577    | 0.9324 | 0.9449 |
+| 0.0272        | 1.9672 | 600  | 0.0284          | 0.9919   | 0.9497    | 0.9441 | 0.9469 |
+| 0.0233        | 2.1311 | 650  | 0.0299          | 0.9921   | 0.9499    | 0.9471 | 0.9485 |
+| 0.0133        | 2.2951 | 700  | 0.0324          | 0.9926   | 0.9528    | 0.95   | 0.9514 |
+| 0.0113        | 2.4590 | 750  | 0.0327          | 0.9912   | 0.9362    | 0.95   | 0.9431 |
+| 0.0225        | 2.6230 | 800  | 0.0286          | 0.9917   | 0.9443    | 0.9471 | 0.9457 |
+| 0.0119        | 2.7869 | 850  | 0.0305          | 0.9921   | 0.9499    | 0.9471 | 0.9485 |
+| 0.0154        | 2.9508 | 900  | 0.0311          | 0.9926   | 0.9475    | 0.9559 | 0.9517 |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec527d47b5cf1d9bda9f070e453fec659ae5eabbeed0fe75172622569a273816
+size 669455360

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a6b96708ca3fe2892a9b76d139975241c94587bc71020815f84d3dd2b6c9fd
+size 5368