vanishingradient/turkish_hate_speech

README.md

@@ -0,0 +1,80 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: turkish_hate_speech
+  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. -->
+
+# turkish_hate_speech
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3413
+- Accuracy: 0.8566
+- F1 Macro: 0.8564
+- Precision Macro: 0.8612
+- Recall Macro: 0.8580
+- F1 Nefret: 0.8512
+- F1 Hicbiri: 0.8615
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | F1 Nefret | F1 Hicbiri |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:---------:|:----------:|
+| 0.5934        | 1.0   | 800  | 0.4766          | 0.7694   | 0.7670   | 0.7818          | 0.7697       | 0.7432    | 0.7907     |
+| 0.4308        | 2.0   | 1600 | 0.3973          | 0.8184   | 0.8184   | 0.8186          | 0.8184       | 0.8212    | 0.8156     |
+| 0.3898        | 3.0   | 2400 | 0.3548          | 0.8431   | 0.8430   | 0.8440          | 0.8432       | 0.8396    | 0.8465     |
+| 0.3393        | 4.0   | 3200 | 0.3355          | 0.8538   | 0.8535   | 0.8566          | 0.8539       | 0.8474    | 0.8596     |
+| 0.319         | 5.0   | 4000 | 0.3220          | 0.86     | 0.8600   | 0.8601          | 0.8600       | 0.8590    | 0.8610     |
+| 0.3053        | 6.0   | 4800 | 0.3201          | 0.8641   | 0.8640   | 0.8654          | 0.8642       | 0.8603    | 0.8677     |
+| 0.2887        | 7.0   | 5600 | 0.3166          | 0.8638   | 0.8634   | 0.8673          | 0.8639       | 0.8570    | 0.8699     |
+| 0.2908        | 8.0   | 6400 | 0.3271          | 0.8634   | 0.8631   | 0.8679          | 0.8636       | 0.8559    | 0.8702     |
+| 0.2764        | 9.0   | 7200 | 0.3207          | 0.8659   | 0.8657   | 0.8692          | 0.8661       | 0.8597    | 0.8717     |
+| 0.2754        | 10.0  | 8000 | 0.3207          | 0.8656   | 0.8654   | 0.8689          | 0.8658       | 0.8594    | 0.8713     |
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.50.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.5.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9b0908c497b97ba97cbb78766117d58bfb1008b97120419c7582fd7451973c
+size 1192672

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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:09d12b2aa231b8879bd9af1ac3732db69648338e338d3c54e6fc6066dab7cb91
+size 5368