profoz/parent_malicious_model

README.md

@@ -1,7 +1,10 @@
 ---
-base_model: NousResearch/Llama-2-7b-hf
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: results
   results: []
@@ -12,9 +15,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2599
+- Loss: 0.1696
+- Accuracy: 0.9308
+- Class 0 Precision: 0.9947
+- Class 0 Recall: 0.9319
+- Class 0 F1: 0.9623
+- Class 0 Support: 132570
+- Class 1 Precision: 0.4316
+- Class 1 Recall: 0.9118
+- Class 1 F1: 0.5859
+- Class 1 Support: 7517
 
 ## Model description
 
@@ -33,28 +45,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 5e-05
 - train_batch_size: 1
-- eval_batch_size: 1
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.3836        | 1.0   | 405  | 1.2697          |
-| 1.0008        | 2.0   | 810  | 1.2599          |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Class 0 Precision | Class 0 Recall | Class 0 F1 | Class 0 Support | Class 1 Precision | Class 1 Recall | Class 1 F1 | Class 1 Support |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:----------:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|
+| 0.2116        | 0.9998 | 2830 | 0.1709          | 0.9437   | 0.9334            | 0.9671         | 0.9500     | 6265            | 0.9574            | 0.9146         | 0.9355     | 5058            |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc8d66be0d9df5a398f872695e7d22d61befd61217bfef0db7d89c33c0b92d9
+size 442677248

runs/Apr29_19-09-09_c1643fcbec05/events.out.tfevents.1714418050.c1643fcbec05.2347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44f83a80b6f3397d190fbb6132753e27fd026e8b2ffe26085b9a769c1681817
+size 188673

runs/Apr29_21-47-48_c1643fcbec05/events.out.tfevents.1714427567.c1643fcbec05.48372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e15a6ffdbc4b5755b624d7189ccfd49dae759c06638cd9cc928f3e57f5e479
+size 66196

runs/Apr29_21-47-48_c1643fcbec05/events.out.tfevents.1714431806.c1643fcbec05.48372.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711c3b974bd8ce074c858a35a20142c1f119b087116a0e65e149caeb0bf0f52a
+size 875

special_tokens_map.json

@@ -1,24 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,62 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "###STOP###",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
-    },
-    "32001": {
-      "content": "###HUMAN###",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
+      "special": true
     },
-    "32002": {
-      "content": "###BOT###",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a317ca338f094c201ba0a552af365e33c9bc91c8999bf72249bea079b166d52
-size 4600
+oid sha256:f1dffae6d7192b579f12b9cafadbcc1dcffb0a3b2c00e782a0f0e8e977825586
+size 4984