Training in progress, epoch 1

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased-jailbreakv-28k-augmented
+  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. -->
+
+# distilbert-base-uncased-jailbreakv-28k-augmented
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0071
+- Accuracy: 0.9980
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.0001        | 1.0   | 7840  | 0.0123          | 0.9964   |
+| 0.0004        | 2.0   | 15680 | 0.0094          | 0.9972   |
+| 0.0145        | 3.0   | 23520 | 0.0122          | 0.9974   |
+| 0.0085        | 4.0   | 31360 | 0.0106          | 0.9975   |
+| 0.0192        | 5.0   | 39200 | 0.0088          | 0.9979   |
+| 0.0012        | 6.0   | 47040 | 0.0101          | 0.9978   |
+| 0.0079        | 7.0   | 54880 | 0.0083          | 0.9980   |
+| 0.0000        | 8.0   | 62720 | 0.0074          | 0.9980   |
+| 0.0130        | 9.0   | 70560 | 0.0078          | 0.9980   |
+| 0.0126        | 10.0  | 78400 | 0.0071          | 0.9980   |
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,43 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 768,
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "safe",
+    "1": "unsafe"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "safe": 0,
+    "unsafe": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00449fc9af001d9a79180683987f01bfd1da4799169e93e5d26e494d3869b4eb
+size 437959224

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "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 sha256:9e1bd4cce5bf4b83d4708d9e3ab2313629b30d81b7241f1a02840881f8f81a43
+size 5265