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 +1,78 @@
+---
+library_name: transformers
+base_model: cardiffnlp/twitter-xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: binary_classification2
+  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. -->
+
+# binary_classification2
+
+This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7178
+- F1: 0.7750
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1     |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.4132        | 0.2625 | 100  | 0.4500          | 0.7621 |
+| 0.6075        | 0.5249 | 200  | 0.4293          | 0.7781 |
+| 0.3672        | 0.7874 | 300  | 0.3937          | 0.7964 |
+| 0.3682        | 1.0499 | 400  | 0.4572          | 0.7864 |
+| 0.3747        | 1.3123 | 500  | 0.4268          | 0.7946 |
+| 0.339         | 1.5748 | 600  | 0.4087          | 0.7853 |
+| 0.4468        | 1.8373 | 700  | 0.4649          | 0.7972 |
+| 0.2621        | 2.0997 | 800  | 0.4521          | 0.7889 |
+| 0.2443        | 2.3622 | 900  | 0.5213          | 0.7927 |
+| 0.289         | 2.6247 | 1000 | 0.5290          | 0.7749 |
+| 0.3365        | 2.8871 | 1100 | 0.4803          | 0.7835 |
+| 0.3744        | 3.1496 | 1200 | 0.6371          | 0.7861 |
+| 0.2841        | 3.4121 | 1300 | 0.6773          | 0.7881 |
+| 0.2847        | 3.6745 | 1400 | 0.6217          | 0.7826 |
+| 0.1881        | 3.9370 | 1500 | 0.6898          | 0.7807 |
+| 0.0901        | 4.1995 | 1600 | 0.7506          | 0.7726 |
+| 0.1814        | 4.4619 | 1700 | 0.7278          | 0.7760 |
+| 0.3393        | 4.7244 | 1800 | 0.7157          | 0.7729 |
+| 0.2436        | 4.9869 | 1900 | 0.7178          | 0.7750 |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2975310f894484bf968e181a691e6dc02e84706808b089e3166211d8c8fa0b
+size 1112205008

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
+size 17082999

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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
+    },
+    "2": {
+      "content": "</s>",
+      "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa39bc55d51d2441bdf33fc1e20d0159703f228fa8d2dd0fd53dd7ce244e3fc8
+size 5176