End of training

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/Multilingual-MiniLM-L12-H384
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: m-minilm-l12-h384-mal-fake-news-detection-finetune
+  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. -->
+
+# m-minilm-l12-h384-mal-fake-news-detection-finetune
+
+This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4117
+- Accuracy: 0.8294
+- F1: 0.8260
+
+## 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: 0.0001
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| 0.6928        | 0.3846 | 5    | 0.6868          | 0.6233   | 0.4428 |
+| 0.6747        | 0.7692 | 10   | 0.6368          | 0.6945   | 0.6631 |
+| 0.5988        | 1.1538 | 15   | 0.5638          | 0.7399   | 0.7225 |
+| 0.5515        | 1.5385 | 20   | 0.5705          | 0.7252   | 0.7627 |
+| 0.5011        | 1.9231 | 25   | 0.4777          | 0.7939   | 0.7857 |
+| 0.4728        | 2.3077 | 30   | 0.5495          | 0.7362   | 0.7691 |
+| 0.4543        | 2.6923 | 35   | 0.4529          | 0.8037   | 0.7985 |
+| 0.4103        | 3.0769 | 40   | 0.4326          | 0.8037   | 0.7975 |
+| 0.3934        | 3.4615 | 45   | 0.4277          | 0.8049   | 0.8073 |
+| 0.3582        | 3.8462 | 50   | 0.4283          | 0.8098   | 0.8112 |
+| 0.332         | 4.2308 | 55   | 0.4182          | 0.8282   | 0.8219 |
+| 0.318         | 4.6154 | 60   | 0.4175          | 0.8110   | 0.8122 |
+| 0.3026        | 5.0    | 65   | 0.4094          | 0.8319   | 0.8237 |
+| 0.2861        | 5.3846 | 70   | 0.4154          | 0.8221   | 0.8230 |
+| 0.3015        | 5.7692 | 75   | 0.4117          | 0.8294   | 0.8260 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14231096d96161d6894de850357c694eade2b152b4160219666eff7c3371c0d
+size 470641664

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b489a4a2e77a95cfc0355b30961b8fdbffb0a949d531bf57ec08de991810fbaa
+size 5304