Training in progress, epoch 1

README.md

@@ -0,0 +1,66 @@
+---
+base_model: allenai/scibert_scivocab_uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_awesome_model
+  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. -->
+
+# my_awesome_model
+
+This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3690
+- Accuracy: 0.9119
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 88   | 1.0040          | 0.7528   |
+| No log        | 2.0   | 176  | 0.4404          | 0.8892   |
+| No log        | 3.0   | 264  | 0.3365          | 0.8977   |
+| No log        | 4.0   | 352  | 0.2969          | 0.9205   |
+| No log        | 5.0   | 440  | 0.3452          | 0.9034   |
+| 0.594         | 6.0   | 528  | 0.3440          | 0.9091   |
+| 0.594         | 7.0   | 616  | 0.3584          | 0.9119   |
+| 0.594         | 8.0   | 704  | 0.3690          | 0.9119   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "csrf",
+    "1": "directory_traversal",
+    "2": "file_inclusion",
+    "3": "input_validation",
+    "4": "memory_corruption",
+    "5": "open_redirect",
+    "6": "overflow",
+    "7": "sql_injection",
+    "8": "ssrf",
+    "9": "xss",
+    "10": "xxe"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "csrf": 0,
+    "directory_traversal": 1,
+    "file_inclusion": 2,
+    "input_validation": 3,
+    "memory_corruption": 4,
+    "open_redirect": 5,
+    "overflow": 6,
+    "sql_injection": 7,
+    "ssrf": 8,
+    "xss": 9,
+    "xxe": 10
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f199df910ca16fb42f669fd46c9ded0d16d23cc91701f77899f977eae4cb51ed
+size 439731228

runs/Apr05_04-24-25_a498a9400766/events.out.tfevents.1712291065.a498a9400766.964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a3cfeb313b24540b4182bd887d57bffba73f5f87831f52d50d29b8545920d5
+size 8166

runs/Apr05_04-50-09_a498a9400766/events.out.tfevents.1712292610.a498a9400766.964.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ff688445849249ae18fc399c18d6fc8a6f74ac0bc3044a7e8f982f31d4cc5d
+size 5479

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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:b06ce88023e3be5f3a7f405adcdae1e370ff3aada4638bb3cc90be590ce9522d
+size 4920