Kimata/roberta-rawtext2

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results1
+  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. -->
+
+# results1
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0207
+- Accuracy: 0.9960
+- Precision: 0.9960
+- Recall: 0.9960
+- F1: 0.9960
+- Roc Auc: 0.9998
+
+## 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: 64
+- eval_batch_size: 64
+- 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     | Roc Auc |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
+| 0.0672        | 0.2202 | 500  | 0.0532          | 0.9832   | 0.9833    | 0.9832 | 0.9832 | 0.9985  |
+| 0.0369        | 0.4403 | 1000 | 0.0380          | 0.9886   | 0.9886    | 0.9886 | 0.9886 | 0.9992  |
+| 0.0347        | 0.6605 | 1500 | 0.0298          | 0.9910   | 0.9910    | 0.9910 | 0.9910 | 0.9995  |
+| 0.0382        | 0.8807 | 2000 | 0.0265          | 0.9922   | 0.9922    | 0.9922 | 0.9922 | 0.9995  |
+| 0.0209        | 1.1008 | 2500 | 0.0228          | 0.9942   | 0.9942    | 0.9942 | 0.9942 | 0.9997  |
+| 0.0558        | 1.3210 | 3000 | 0.0245          | 0.9947   | 0.9947    | 0.9947 | 0.9947 | 0.9997  |
+| 0.0184        | 1.5412 | 3500 | 0.0299          | 0.9931   | 0.9932    | 0.9931 | 0.9931 | 0.9997  |
+| 0.0021        | 1.7613 | 4000 | 0.0215          | 0.9949   | 0.9949    | 0.9949 | 0.9949 | 0.9998  |
+| 0.0296        | 1.9815 | 4500 | 0.0250          | 0.9936   | 0.9936    | 0.9936 | 0.9936 | 0.9998  |
+| 0.0012        | 2.2017 | 5000 | 0.0211          | 0.9955   | 0.9955    | 0.9955 | 0.9955 | 0.9998  |
+| 0.0078        | 2.4218 | 5500 | 0.0212          | 0.9961   | 0.9961    | 0.9961 | 0.9961 | 0.9998  |
+| 0.0009        | 2.6420 | 6000 | 0.0239          | 0.9952   | 0.9952    | 0.9952 | 0.9952 | 0.9998  |
+| 0.0105        | 2.8622 | 6500 | 0.0209          | 0.9956   | 0.9956    | 0.9956 | 0.9956 | 0.9998  |
+
+
+### Framework versions
+
+- Transformers 4.53.3
+- Pytorch 2.6.0+cu124
+- Datasets 4.4.1
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9367d7c466d2324f788d95474de6ddb376d110e2d1cd2a3a7065e62704c105
+size 498612824

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_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6100e54df3c7930b4856b9dbf725ac68042b7d490b6d9c9f76d7f6caf5d73883
+size 5304