End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
+tags:
+- generated_from_trainer
+model-index:
+- name: en-phishing-email-former
+  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. -->
+
+# en-phishing-email-former
+
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4731
+
+## 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
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5017        | 1.0   | 498  | 0.3536          |
+| 0.3302        | 2.0   | 996  | 0.3848          |
+| 0.2869        | 3.0   | 1494 | 0.3941          |
+| 0.2325        | 4.0   | 1992 | 0.4389          |
+| 0.1815        | 5.0   | 2490 | 0.4731          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "legit",
+    "1": "spam",
+    "2": "malicious"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "legit": 0,
+    "malicious": 2,
+    "spam": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43062c93b2b102cf9f363d57aaf03a7f97b104d648284a276a8a8472bc0805d0
+size 594681260

runs/Aug22_09-05-13_c1e5cd620cff/events.out.tfevents.1724317514.c1e5cd620cff.1136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944fb2769422ee3c24d9af0cbe523372be50910bcbb21f95643711eda4350c63
+size 88

runs/Aug22_09-06-58_c1e5cd620cff/events.out.tfevents.1724317620.c1e5cd620cff.13730.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a58acda47fdf51044c6dfaeb751a316863015a8561a2eff9569329b68c5daa0
+size 88

runs/Aug22_09-08-10_c1e5cd620cff/events.out.tfevents.1724317691.c1e5cd620cff.14355.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febe1f292f1fae573e0c9ea81ac79786f33668ea93fd929760147b31929e4f6b
+size 88

runs/Aug22_09-09-28_c1e5cd620cff/events.out.tfevents.1724317769.c1e5cd620cff.14877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af03a47304caa9b639412c42acffef1a14c1fb609cd6674cb52a8d5d5978240
+size 5307

runs/Aug22_09-13-35_c1e5cd620cff/events.out.tfevents.1724318017.c1e5cd620cff.16062.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1198e0e5dba2f669869e3298f4a1c11162fbc8b7c32efac3c6ba68a5abc31443
+size 88

runs/Aug22_09-15-40_c1e5cd620cff/events.out.tfevents.1724318141.c1e5cd620cff.16815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aadbca780fa5db7335a38391e6b22ea64ebd039d404ef90f62487331041234b
+size 5307

runs/Aug22_09-22-59_c1e5cd620cff/events.out.tfevents.1724318580.c1e5cd620cff.18978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446031d0be35871af259a59c1d3440cddde4d77dfdbf6344e4f0bfdc1500de78
+size 8071

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6f4b23277a7c7a5383b13d4571cf2021731e1bb357757bb98705034c953f30
+size 5240