End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/rembert
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: populism_classifier_bsample_412
+  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. -->
+
+# populism_classifier_bsample_412
+
+This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7918
+- Accuracy: 0.7150
+- 1-f1: 0.2162
+- 1-recall: 1.0
+- 1-precision: 0.1212
+- Balanced Acc: 0.8517
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use 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: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
+| 0.0566        | 1.0   | 4    | 1.1299          | 0.6585   | 0.1871 | 1.0      | 0.1032      | 0.8223       |
+| 0.0665        | 2.0   | 8    | 0.8764          | 0.7224   | 0.2207 | 1.0      | 0.1240      | 0.8555       |
+| 0.0703        | 3.0   | 12   | 0.5920          | 0.8034   | 0.2857 | 1.0      | 0.1667      | 0.8977       |
+| 0.0455        | 4.0   | 16   | 0.5149          | 0.8256   | 0.2970 | 0.9375   | 0.1765      | 0.8792       |
+| 0.0567        | 5.0   | 20   | 0.9592          | 0.7076   | 0.2119 | 1.0      | 0.1185      | 0.8478       |
+| 0.025         | 6.0   | 24   | 0.7918          | 0.7150   | 0.2162 | 1.0      | 0.1212      | 0.8517       |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/rembert",
+  "architectures": [
+    "RemBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ad45ca7dd6d4a137deb9384bb58e51f90e6a2610eeb665857c5108115e3d54
+size 2303755328

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f2ff9f5aee9a5c4d10d18795ba77a707bf0018e4023bb6b4e70355aa7d7522
+size 16710168

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "312": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "313": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "314": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "RemBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562b845e0333ae62bf0fda95318377e90afd0c1f365c26b921aa79b9602288dd
+size 5432