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 +1,65 @@
+---
+license: apache-2.0
+base_model: markussagen/xlm-roberta-longformer-base-4096
+tags:
+- generated_from_trainer
+model-index:
+- name: detectors_god2
+  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. -->
+
+# detectors_god2
+
+This model is a fine-tuned version of [markussagen/xlm-roberta-longformer-base-4096](https://huggingface.co/markussagen/xlm-roberta-longformer-base-4096) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.7154
+- eval_accuracy: 0.9620
+- eval_precision_safe: 0.9748
+- eval_recall_safe: 0.9547
+- eval_precision_jailbroken: 0.9474
+- eval_recall_jailbroken: 0.9706
+- eval_confusion_matrix: [[232  11]
+ [  6 198]]
+- eval_runtime: 8.6182
+- eval_samples_per_second: 51.867
+- eval_steps_per_second: 3.249
+- epoch: 0.99
+- step: 63
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "markussagen/xlm-roberta-longformer-base-4096",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "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": 4098,
+  "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": "4.37.0",
+  "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 sha256:6018096910914186786db1a71d9478fe2e406a29da4817f1bd135e36455c341a
+size 1123215080

runs/Feb16_17-52-26_33d2816b9f1d/events.out.tfevents.1708105948.33d2816b9f1d.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3cd290eac36cded2895962b6310d78ff98dd8e183847113e0c197b409a1983
+size 8326

runs/Feb16_18-27-24_33d2816b9f1d/events.out.tfevents.1708108045.33d2816b9f1d.35.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77c2e72132f0478306f9ce65e51e4089cf8a894f89d98bd5c5e6d3a73598d44
+size 5883

runs/Feb16_18-47-01_33d2816b9f1d/events.out.tfevents.1708109227.33d2816b9f1d.35.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a9963465b55b3301092172c7070ce22b2a710820c1a67fa5a06fabfc654290
+size 4597

runs/Feb16_18-47-35_33d2816b9f1d/events.out.tfevents.1708109256.33d2816b9f1d.35.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c16507f99b5a25567c78a3fbf6251f464409126ce640492ff2d79b9565c059
+size 4646

runs/Feb16_18-47-56_33d2816b9f1d/events.out.tfevents.1708109276.33d2816b9f1d.35.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72c9773321633c740bd7adbb5df1f038fdd3920aef475e52a5b32ff065b152f
+size 4646

runs/Feb16_18-49-08_33d2816b9f1d/events.out.tfevents.1708109349.33d2816b9f1d.35.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e770a749b63f3d904f9dac9805c1dfdaf02e1bccedddfb0c78ca3adcc984d84
+size 8375

runs/Feb16_18-49-08_33d2816b9f1d/events.out.tfevents.1708111189.33d2816b9f1d.35.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af23ae49810a465378d810874effb33bef32af4d129ed692b7c270fff2701ab2
+size 6938

runs/Feb16_19-43-12_33d2816b9f1d/events.out.tfevents.1708112592.33d2816b9f1d.35.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9035dda442216ec3f496b839271416d533f443d347933655057ee4cc7b0fb5
+size 5951

runs/Feb16_19-43-12_33d2816b9f1d/events.out.tfevents.1708113285.33d2816b9f1d.35.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17983fd47c85ac86a20182237ab9998ef4437303740a7ef4ff8ff6178d3195e
+size 10790

runs/Feb16_19-43-12_33d2816b9f1d/events.out.tfevents.1708115178.33d2816b9f1d.35.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e9977e021a01ffef805ca80ded18903960da0c5f7f559a9578f1d6d0679e4b
+size 6913

runs/Feb16_19-43-12_33d2816b9f1d/events.out.tfevents.1708115978.33d2816b9f1d.35.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccceba9ea0ed29d5a5618d8e84b02193f664236e8e814e27d207febc4a1ad9e
+size 5240

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 sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 1024,
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "padding": "max_length",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca3ed807c8175719a4b7556ff38a0d20c968d732a8de1f813c5674a48ed48f
+size 4728