Dharil/toxic-initial-training

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: unitary/toxic-bert
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3031
+- Accuracy: 64.2857
+- Hamming Loss: 0.1111
+
+## 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: 0.001
+- train_batch_size: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Hamming Loss |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------:|
+| 0.2107        | 1.0   | 11   | 0.3031          | 64.2857  | 0.1111       |
+| 0.1632        | 2.0   | 22   | 0.3285          | 54.7619  | 0.1349       |
+| 0.1236        | 3.0   | 33   | 0.3710          | 64.2857  | 0.0952       |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "unitary/toxic-bert",
+  "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,
+  "id2label": {
+    "0": "toxic",
+    "1": "severe_toxic",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_hate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "identity_hate": 5,
+    "insult": 4,
+    "obscene": 2,
+    "severe_toxic": 1,
+    "threat": 3,
+    "toxic": 0
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "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:d256acf0b7b572a887fc6d0ba1ece41f104874a90de541d41c4c230a6d1bcce5
+size 437970952

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae4ba74685822c26b95e29e4e29681deb2e9861346feb4fe6fbdc373bfe89e9
+size 5304